© 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. 22-GEMMASCOPE-RES-131K
    7. 73308
    Prev
    Next
    INDEX
    Explanations

    code file paths

    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_22/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
     this
    -2.11
     what
    -1.39
     new
    -1.39
     or
    -1.34
     for
    -1.28
     and
    -1.27
     from
    -1.23
     by
    -1.21
     after
    -1.20
    cún
    -1.20
    POSITIVE LOGITS
    では
    1.33
    で
    1.22
    Bjs
    1.20
    毟
    1.15
    しかし
    1.13
    薗
    1.13
    determined
    1.13
     velg
    1.09
     ™
    1.09
     ares
    1.08
    Activations Density 0.013%

    No Known Activations