© 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. 30752
    Prev
    Next
    INDEX
    Explanations

    questions asking how

    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
    Loads
    -0.86
    buscar
    -0.84
    差点
    -0.82
     errs
    -0.81
     amorti
    -0.79
     Renewed
    -0.79
    Efficient
    -0.78
    marc
    -0.78
     evan
    -0.77
     中身
    -0.77
    POSITIVE LOGITS
     was
    1.23
     long
    1.16
     about
    0.99
    готовка
    0.93
     is
    0.91
     old
    0.89
     dår
    0.89
     vanske
    0.86
     are
    0.85
     {}));
    0.83
    Activations Density 0.017%

    No Known Activations