© 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. 22-GEMMASCOPE-RES-131K
    4. 70452
    Prev
    Next
    INDEX
    Explanations

    drug names ending in )

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

    brand names of pharmaceutical drugs.

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

    The neuron activates on substrings of pharmaceutical drug names and brand names (e.g. “Camp,” “Avastin,” “Tamiflu,” “Taxotere,” “Septra,” “Dyazide,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    posY
    -1.27
    CultureInfo
    -1.26
    国道
    -1.22
    cides
    -1.21
     掃除
    -1.20
    ֠
    -1.12
    ここは
    -1.10
     dollari
    -1.09
     of
    -1.08
     they
    -1.08
    POSITIVE LOGITS
     norvég
    1.43
     by
    1.37
     cucharadita
    1.34
     or
    1.28
     hidratante
    1.22
     meub
    1.17
     perpé
    1.16
    ahora
    1.16
    DAFTAR
    1.15
     faſt
    1.13
    Activations Density 0.033%

    No Known Activations