© 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. 129142
    Prev
    Next
    INDEX
    Explanations

    vocational, economics, health, FFA

    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
     niks
    -1.64
    ICIAS
    -1.59
     GROUPS
    -1.55
    ть
    -1.52
     SEPTEMBER
    -1.50
     welk
    -1.47
     heer
    -1.45
     bruin
    -1.42
    认知
    -1.41
     janu
    -1.40
    POSITIVE LOGITS
    </strong>
    2.20
     both
    2.00
     more
    1.83
     that
    1.73
     this
    1.71
     almost
    1.67
     even
    1.66
     greatly
    1.62
     profoundly
    1.61
     helping
    1.60
    Activations Density 0.008%

    No Known Activations