© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101692
    Prev
    Next
    INDEX
    Explanations

    string delimiters

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

    commas in lists or arrays within programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on quoted alphabetic string literals (e.g. sequences of letters in quotes).

    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
    providedIn
    -1.95
     it
    -1.83
     where
    -1.80
    دانلود
    -1.66
    ?”
    -1.59
     from
    -1.59
    はこんな感じ
    -1.55
    Despite
    -1.55
     have
    -1.54
    をご覧ください
    -1.53
    POSITIVE LOGITS
     alumno
    1.95
    xelles
    1.84
    ";
    1.80
    놋
    1.77
    ти
    1.76
     technische
    1.69
    neos
    1.67
    炱
    1.66
    いえば
    1.66
     whatnot
    1.63
    Activations Density 0.031%

    No Known Activations