© 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. 31092
    Prev
    Next
    INDEX
    Explanations

    code imports and tests

    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
    Сон
    -0.81
    arme
    -0.79
    Clima
    -0.76
     despite
    -0.73
    distan
    -0.73
    republik
    -0.71
     versuchen
    -0.71
     spite
    -0.71
     ボディ
    -0.70
    linky
    -0.69
    POSITIVE LOGITS
    require
    0.94
    stor
    0.89
     mem
    0.89
     programmable
    0.88
     Fad
    0.88
     reverted
    0.84
     stor
    0.84
    renaline
    0.79
    Matth
    0.79
     sô
    0.78
    Activations Density 0.001%

    No Known Activations