© 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. 10692
    Prev
    Next
    INDEX
    Explanations

    increase in

    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
    We
    -3.31
    *
    -3.20
    </b>
    -3.17
    —
    -3.03
    /
    -2.81
    –
    -2.81
     
    -2.80
     Brought
    -2.73
    ––
    -2.69
    老婆
    -2.69
    POSITIVE LOGITS
    韪
    2.84
    ◳
    2.78
     motores
    2.78
    เกง
    2.77
    潆
    2.77
    warnai
    2.72
     toneladas
    2.67
    IZACIÓN
    2.66
     parachoque
    2.63
    ↵
    2.61
    Activations Density 0.046%

    No Known Activations