© 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. 129852
    Prev
    Next
    INDEX
    Explanations

    athlete orvictorylap

    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
     Acerca
    -1.08
    Vía
    -1.01
    uckt
    -1.00
     spoko
    -0.96
     Fácil
    -0.96
     embrague
    -0.95
     مي‌
    -0.94
    ربع
    -0.93
    が好き
    -0.93
     景观
    -0.93
    POSITIVE LOGITS
    antina
    0.88
    まれた
    0.88
    ↵↵↵↵↵
    0.86
     skå
    0.86
     чтобы
    0.86
    věr
    0.82
     samtidigt
    0.82
     aja
    0.81
     может
    0.81
    ↵↵↵↵
    0.80
    Activations Density 0.009%

    No Known Activations