© 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. 13186
    Prev
    Next
    INDEX
    Explanations

    available fa, type replace, { name

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

    This neuron responds to non-word, code-style punctuation and symbols (e.g. braces, hashes, angle brackets, macros, operators)—essentially detecting code syntax tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     to
    -2.88
     that
    -2.38
     when
    -2.31
     during
    -2.27
     which
    -2.03
     at
    -2.02
     as
    -1.92
     tells
    -1.92
    er
    -1.91
     before
    -1.89
    POSITIVE LOGITS
    ſa
    2.02
    旆
    2.02
    齪
    1.84
     traductions
    1.78
    ★☆
    1.72
     congrès
    1.71
     matchs
    1.71
    皛
    1.70
     prestations
    1.68
    𓐍
    1.67
    Activations Density 0.004%

    No Known Activations