© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12314
    Prev
    Next
    INDEX
    Explanations

    people and places

    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
    pshots
    -1.47
    while
    -1.43
     have
    -1.32
    Similar
    -1.31
     alguns
    -1.30
     alcuni
    -1.30
     Ursache
    -1.30
    Their
    -1.29
    сили
    -1.28
     Körpers
    -1.27
    POSITIVE LOGITS
    <bos>
    1.72
    ↵
    1.59
     will
    1.53
     formaggio
    1.36
     that
    1.33
    ɵɵelementEnd
    1.33
     of
    1.29
    }:${
    1.27
     which
    1.26
     afges
    1.22
    Activations Density 0.244%

    No Known Activations