© 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. 9657
    Prev
    Next
    INDEX
    Explanations

    code syntax constructs

    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
    鶿
    -1.91
    şil
    -1.88
     avantages
    -1.83
    🫃
    -1.80
    mappedBy
    -1.78
    𓁹
    -1.78
    ౧
    -1.73
     fermer
    -1.71
     ارسال
    -1.70
     préférences
    -1.70
    POSITIVE LOGITS
     but
    2.55
     when
    2.25
     from
    2.16
     both
    2.08
     with
    2.06
     During
    2.06
     then
    2.02
     everything
    1.94
     There
    1.88
     With
    1.78
    Activations Density 0.003%

    No Known Activations