© 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. 34-GEMMASCOPE-RES-131K
    4. 98524
    Prev
    Next
    INDEX
    Explanations

    gallbladder, gallstone, gallantry, gallate

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

    the word "gall" and its variations like "gallbladder" or "gallant" in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Noc
    -0.73
     corpi
    -0.73
    cino
    -0.71
     корпуса
    -0.69
     вовсе
    -0.68
    世纪
    -0.67
     schul
    -0.67
     sos
    -0.67
     Barang
    -0.66
    件
    -0.66
    POSITIVE LOGITS
     Galla
    0.92
     Gall
    0.84
    Gall
    0.80
    gher
    0.79
    antly
    0.79
     Premiership
    0.78
     bladder
    0.77
     especí
    0.76
     Poll
    0.75
     GALL
    0.74
    Activations Density 0.038%

    No Known Activations