© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105932
    Prev
    Next
    INDEX
    Explanations

    Typhoon and Typhimurium bacteria

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of "typhoon" or "typhimurium" (a Salmonella strain) and their variations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on words beginning with the character sequence “typh,” such as “Typhoon” or “typhimurium.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    tokens containing the letter sequence “typ” (especially as an initial “typh-” prefix), with strongest activation when it starts a prominent noun.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "Typhoon" or variants of "typhimurium" (a Salmonella species).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    -3.14
    -"
    -2.81
    !"
    -2.70
     ),
    -2.64
    镚
    -2.50
    )$,
    -2.45
    ,"
    -2.41
    ".
    -2.36
    ...."
    -2.34
    ;"
    -2.28
    POSITIVE LOGITS
    {
    2.11
    鈇
    2.09
    ㈰
    2.08
    牁
    2.05
    at
    2.03
    .
    2.02
    Ꮄ
    1.98
    い
    1.90
    凼
    1.89
    𐍆
    1.88
    Activations Density 0.003%

    No Known Activations