© 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. 9159
    Prev
    Next
    INDEX
    Explanations

    method parameter definitions

    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
    chtete
    -1.29
    dious
    -1.27
    LECTIONS
    -1.26
    gheny
    -1.20
    爀
    -1.19
    igten
    -1.17
    phère
    -1.17
    vedades
    -1.17
     wees
    -1.16
    𝕐
    -1.16
    POSITIVE LOGITS
    They
    1.80
     /
    1.77
     they
    1.69
     that
    1.68
     other
    1.65
    <h2>
    1.41
    .
    1.29
     data
    1.27
     others
    1.27
    是吗
    1.25
    Activations Density 0.013%

    No Known Activations