© 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. 3214
    Prev
    Next
    INDEX
    Explanations

    buttmakers

    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
    hounds
    -0.84
     aunque
    -0.83
     記事
    -0.77
     完成
    -0.75
    io
    -0.74
     lakini
    -0.73
    ry
    -0.73
    ふう
    -0.72
     raisins
    -0.72
     作成
    -0.72
    POSITIVE LOGITS
    chers
    1.10
    lers
    0.98
    凡
    0.98
    ting
    0.94
    ressed
    0.91
     Butler
    0.91
    ละ
    0.90
    combe
    0.87
    HOLE
    0.87
    couleur
    0.85
    Activations Density 0.026%

    No Known Activations