© 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. 22-GEMMASCOPE-RES-131K
    7. 73372
    Prev
    Next
    INDEX
    Explanations

    Cook of the Month, symphonic, Hackin

    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
     makro
    -0.97
     Vamos
    -0.96
    Другие
    -0.95
     exager
    -0.94
     lenght
    -0.90
    なりません
    -0.89
    toko
    -0.85
     spart
    -0.84
     Regula
    -0.84
     Tó
    -0.83
    POSITIVE LOGITS
     Football
    1.18
    existsSync
    1.16
     notamment
    1.13
    readFileSync
    1.13
     Teilnehmer
    1.09
     Empfang
    1.04
     وكان
    1.03
    endforeach
    1.02
     urč
    1.02
    漂亮的
    1.00
    Activations Density 0.045%

    No Known Activations