© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102508
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

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

    The neuron fires strongly on non‐alphanumeric symbols (brackets, punctuation, regex metacharacters, backslashes, etc.) typically found in code or regular expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     voleva
    -0.95
    )，
    -0.93
    )、
    -0.91
    ).
    -0.89
    ）.
    -0.89
    )：
    -0.88
     parteci
    -0.88
     مساب
    -0.88
    ）。
    -0.87
    Čo
    -0.87
    POSITIVE LOGITS
     +
    1.23
     !
    1.22
     #
    1.20
     @
    1.16
     "#
    1.07
     *
    1.06
     ~
    1.06
     <
    1.04
     \#
    1.02
     [
    0.99
    Activations Density 0.112%

    No Known Activations