© 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. 58506
    Prev
    Next
    INDEX
    Explanations

    date, public, free, wish, phase

    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
    ærk
    -0.70
    InitVars
    -0.68
    جيل
    -0.65
     Han
    -0.65
    ConverterFactory
    -0.64
    гат
    -0.64
    ˌ
    -0.64
     three
    -0.64
    raseña
    -0.64
     сигнал
    -0.63
    POSITIVE LOGITS
     juu
    0.72
     приве
    0.71
     mondiale
    0.69
    kinin
    0.69
     licencia
    0.68
    mler
    0.67
    Deze
    0.66
     gebraucht
    0.66
     truncated
    0.65
    inola
    0.65
    Activations Density 0.070%

    No Known Activations