© 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. 57220
    Prev
    Next
    INDEX
    Explanations

    Troy Cottam

    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
    upu
    -0.81
    There
    -0.77
    ^(-
    -0.75
    abos
    -0.75
    苫
    -0.74
     هن
    -0.71
     terasa
    -0.71
    pida
    -0.71
     cumulative
    -0.71
     or
    -0.71
    POSITIVE LOGITS
    ographic
    0.84
    freunde
    0.83
     çelik
    0.82
     resor
    0.81
     دختر
    0.81
    duction
    0.81
    tage
    0.80
     Scalars
    0.80
     
    0.79
     sabiduría
    0.78
    Activations Density 0.024%

    No Known Activations