© 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. 14094
    Prev
    Next
    INDEX
    Explanations

    @author documentation 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_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
     pourraient
    -1.58
     You
    -1.56
     gewöhnlich
    -1.52
    illir
    -1.52
     maar
    -1.49
    ступили
    -1.46
     quirky
    -1.45
     ако
    -1.44
     goofy
    -1.42
    ctrica
    -1.41
    POSITIVE LOGITS
     every
    1.84
     some
    1.80
     with
    1.74
     using
    1.70
     all
    1.70
     only
    1.66
    '
    1.62
     these
    1.57
     any
    1.57
     more
    1.57
    Activations Density 0.009%

    No Known Activations