© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129980
    Prev
    Next
    INDEX
    Explanations

    else if

    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_22/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
    haviours
    -1.06
    atized
    -1.00
     bolso
    -0.99
     dati
    -0.97
     vinaigre
    -0.96
     fú
    -0.94
    laß
    -0.93
    //=
    -0.93
     enoj
    -0.93
    ystems
    -0.92
    POSITIVE LOGITS
     if
    1.45
     vielfach
    1.05
     gegenwär
    0.95
     If
    0.94
    最初に
    0.93
     nächsten
    0.93
     kommenden
    0.93
     vielfäl
    0.91
    FDP
    0.90
     إليها
    0.90
    Activations Density 0.002%

    No Known Activations