© 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. 33081
    Prev
    Next
    INDEX
    Explanations

    regular expressions and code syntax

    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
    -2.52
     in
    -2.31
     by
    -1.99
     from
    -1.95
     for
    -1.90
     more
    -1.81
     even
    -1.80
     with
    -1.77
     at
    -1.77
     it
    -1.73
    POSITIVE LOGITS
     unceasing
    1.50
     diriger
    1.48
     idiotic
    1.46
     impromptu
    1.45
     commencer
    1.44
    ఝ
    1.41
     faciliter
    1.41
     retourner
    1.41
     unending
    1.40
     uniquement
    1.39
    Activations Density 0.002%

    No Known Activations