© 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. 10-GEMMASCOPE-RES-131K
    7. 111758
    Prev
    Next
    INDEX
    Explanations

    technical contexts with delimiters

    np_acts-logits-general · gemini-2.5-flash-lite

    closing braces, brackets, or parentheses in mathematical notation and code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     bekym
    -2.00
     normalt
    -1.94
     refroid
    -1.94
     nivå
    -1.92
    极为
    -1.91
     naturlig
    -1.90
    harapkan
    -1.88
     bascul
    -1.77
     étan
    -1.76
     déchir
    -1.76
    POSITIVE LOGITS
     not
    2.27
     a
    2.17
     and
    2.09
     using
    2.03
     the
    2.00
     to
    1.93
     in
    1.87
     what
    1.84
     without
    1.83
     you
    1.82
    Activations Density 0.038%

    No Known Activations