© 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. 26276
    Prev
    Next
    INDEX
    Explanations

    generated code snippets

    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
     my
    -1.82
     this
    -1.68
     before
    -1.67
     with
    -1.67
     all
    -1.66
     most
    -1.61
     some
    -1.56
     more
    -1.55
     in
    -1.52
     on
    -1.52
    POSITIVE LOGITS
     Dinas
    1.81
    這裡
    1.77
    ちょい
    1.73
    さっぱり
    1.73
     solche
    1.72
     pescoço
    1.70
     登山
    1.66
     ayur
    1.66
    ちょ
    1.65
     ซึ่ง
    1.58
    Activations Density 0.000%

    No Known Activations