© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35540
    Prev
    Next
    INDEX
    Explanations

    URLs and file extensions

    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
     on
    -2.34
     had
    -2.13
     for
    -2.05
     four
    -2.00
     or
    -2.00
     three
    -1.98
     in
    -1.97
     two
    -1.97
     an
    -1.96
     at
    -1.96
    POSITIVE LOGITS
     Dinas
    1.96
     insanely
    1.91
     faciliter
    1.89
     luscious
    1.87
     REALLY
    1.82
     AMAZING
    1.79
     unbelievably
    1.78
     wondrous
    1.78
     ludicrous
    1.78
     ridiculously
    1.77
    Activations Density 0.007%

    No Known Activations