© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66795
    Prev
    Next
    INDEX
    Explanations

    second derivative

    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
    嫱
    -1.16
     内衣
    -1.16
     churras
    -1.14
    não
    -1.10
    uebas
    -1.06
     編み
    -1.05
     vna
    -1.02
    pulseira
    -1.02
    anza
    -1.01
    鉺
    -1.00
    POSITIVE LOGITS
     in
    1.27
     –
    1.04
     me
    1.02
     also
    0.98
     On
    0.97
     חד
    0.92
     balance
    0.92
     Balance
    0.91
    !】
    0.90
     piłkarz
    0.90
    Activations Density 0.012%

    No Known Activations