© 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. 111259
    Prev
    Next
    INDEX
    Explanations

    references, after, in, the, he, for, while, at

    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
     your
    -2.42
     this
    -2.23
     either
    -2.11
     you
    -1.83
     You
    -1.81
     their
    -1.78
     new
    -1.76
    🩱
    -1.73
    "),
    -1.70
     Either
    -1.66
    POSITIVE LOGITS
     of
    2.72
     правительства
    1.95
     enfans
    1.88
     prêtres
    1.70
     cristianos
    1.70
    状態で
    1.69
     Theologie
    1.62
     poivre
    1.59
     默认
    1.59
     chré
    1.58
    Activations Density 0.181%

    No Known Activations