© 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. 10-GEMMASCOPE-RES-131K
    7. 100148
    Prev
    Next
    INDEX
    Explanations

    legislative bills, math factors, time for

    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_10/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
     the
    -2.55
    的我
    -1.84
     wherein
    -1.70
     pieles
    -1.66
    ristiano
    -1.66
    子供が
    -1.64
     devoid
    -1.59
     where
    -1.59
     but
    -1.55
     either
    -1.54
    POSITIVE LOGITS
    ophones
    1.88
    naments
    1.73
    chläge
    1.73
    ~~~~~
    1.72
    ização
    1.70
    欒
    1.67
    lettes
    1.66
    💁
    1.63
    uride
    1.60
    🏆
    1.60
    Activations Density 0.074%

    No Known Activations