© 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. 59347
    Prev
    Next
    INDEX
    Explanations

    static code constructs ANN

    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
     gitar
    -1.64
     niedersachsen
    -1.54
    rictive
    -1.53
    菒
    -1.48
    significantly
    -1.48
    prey
    -1.48
    Ｗ
    -1.48
    龌
    -1.48
    しゃぶ
    -1.46
    และ
    -1.45
    POSITIVE LOGITS
    ↵↵
    3.13
     does
    2.27
     has
    2.08
     used
    1.94
     not
    1.84
     can
    1.81
     using
    1.81
     uses
    1.74
     or
    1.74
     new
    1.70
    Activations Density 0.021%

    No Known Activations