© 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. 72547
    Prev
    Next
    INDEX
    Explanations

    locations and structures

    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
    位於
    -1.16
     across
    -1.02
    がいる
    -0.98
     fijne
    -0.93
     naast
    -0.91
     neighbouring
    -0.90
     خوبه
    -0.90
     東京都
    -0.90
    になりたい
    -0.90
     přímo
    -0.90
    POSITIVE LOGITS
     reine
    0.95
    where
    0.93
     Здесь
    0.92
    霎
    0.91
     современной
    0.91
     Allí
    0.90
     vede
    0.86
    Grá
    0.86
    Zdrav
    0.84
    在那里
    0.84
    Activations Density 0.081%

    No Known Activations