© 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. 67055
    Prev
    Next
    INDEX
    Explanations

    brands and acronyms

    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
     with
    -3.08
     more
    -2.09
     from
    -2.09
     during
    -1.86
     after
    -1.77
     without
    -1.76
     for
    -1.69
     three
    -1.66
     one
    -1.60
     etiam
    -1.59
    POSITIVE LOGITS
     who
    2.14
     they
    1.77
     baden
    1.68
     они
    1.68
     feil
    1.64
     deberían
    1.63
     appliquer
    1.62
     فقط
    1.61
     flotte
    1.59
    がありません
    1.59
    Activations Density 0.283%

    No Known Activations