© 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. 16210
    Prev
    Next
    INDEX
    Explanations

    xml closing tags

    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
     for
    -1.79
     in
    -1.71
     (
    -1.63
     of
    -1.52
     from
    -1.30
     this
    -1.29
     -
    -1.28
    !
    -1.28
    .(
    -1.21
    //!
    -1.21
    POSITIVE LOGITS
    푉
    1.52
    Skal
    1.45
    Hilsen
    1.45
     leggera
    1.41
     parteci
    1.41
     richied
    1.40
    Tils
    1.36
    Minden
    1.33
    Ruju
    1.32
    Ciri
    1.31
    Activations Density 0.009%

    No Known Activations