© 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. 10-GEMMASCOPE-RES-131K
    7. 10381
    Prev
    Next
    INDEX
    Explanations

    za or За prefix

    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_10/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
    [
    -2.44
    *
    -2.39
    )
    -2.25
     tetapi
    -2.20
    ’
    -2.09
    ↵↵
    -2.05
    “
    -1.98
    ႐
    -1.95
     dieser
    -1.95
    /
    -1.95
    POSITIVE LOGITS
    噐
    2.50
    鉏
    2.23
    怱
    2.16
    鯷
    2.16
    苼
    2.16
    泚
    2.11
    
    2.06
    我没
    2.05
    ⽼
    2.03
    
    2.02
    Activations Density 0.003%

    No Known Activations