© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19212
    Prev
    Next
    INDEX
    Explanations

    visceral leishmaniasis

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

    acronyms and abbreviations related to medical or technical terms, particularly "VL" (viral load).

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

    The neuron activates on instances of the letter sequence “vl” (e.g. in abbreviations like VL or in instruction mnemonics ending in “vl”).

    oai_token-act-pair · o4-miniTriggered 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
    ↵↵
    -3.22
    ).
    -2.86
    ↵
    -2.75
     garantiza
    -2.61
    a
    -2.53
    ”.
    -2.44
     otorga
    -2.41
    的问道
    -2.28
     ubica
    -2.19
    灩
    -2.19
    POSITIVE LOGITS
    ?"
    3.03
     "
    2.70
    "—
    2.69
    嫆
    2.55
    に来て
    2.53
    ᕮ
    2.53
     bylo
    2.52
    "'
    2.50
     jsou
    2.44
     "'
    2.42
    Activations Density 0.004%

    No Known Activations