© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66885
    Prev
    Next
    INDEX
    Explanations

    by what

    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
     أيض
    -1.40
    1
    -1.33
    Gön
    -1.33
    嬉しいです
    -1.31
     помогает
    -1.31
    锖
    -1.27
    2
    -1.27
     ausein
    -1.26
    ↵↵
    -1.23
    Ciri
    -1.21
    POSITIVE LOGITS
     that
    1.80
    ppsala
    1.38
    来店
    1.34
     with
    1.34
    ℣
    1.31
     */;
    1.28
    ॰
    1.28
     then
    1.23
    новая
    1.23
    住宿
    1.23
    Activations Density 0.053%

    No Known Activations