© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47570
    Prev
    Next
    INDEX
    Explanations

    Div

    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
     ec
    -0.82
    ragen
    -0.73
    peper
    -0.71
    帰
    -0.66
     ước
    -0.66
     Stefano
    -0.65
    考试
    -0.64
     discord
    -0.63
    olo
    -0.63
     McL
    -0.62
    POSITIVE LOGITS
     Finishing
    0.70
    stände
    0.70
    classpath
    0.69
    irce
    0.69
    وانات
    0.68
     gj
    0.67
    лица
    0.64
     IMPLEMENT
    0.64
     atualização
    0.63
    grounds
    0.63
    Activations Density 0.072%

    No Known Activations