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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99525
    Prev
    Next
    INDEX
    Explanations

    list or match

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    漬け
    -0.71
     Modo
    -0.66
    carrying
    -0.64
    squirrel
    -0.64
     Piedra
    -0.63
    🎺
    -0.63
     giriş
    -0.62
     toko
    -0.62
    発言
    -0.61
    qiang
    -0.61
    POSITIVE LOGITS
     würde
    0.69
     أب
    0.69
     Tochter
    0.66
     Bibel
    0.64
    菜
    0.64
    anku
    0.63
    listo
    0.60
    Telephone
    0.60
     КА
    0.60
    ฮ
    0.60
    Activations Density 0.136%

    No Known Activations