© 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. 109159
    Prev
    Next
    INDEX
    Explanations

    variables, functions, and code snippets

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

    This neuron responds to programming-language operators and conditional keywords (e.g. ‘&&’, ‘!’, ‘isset’, pipes “|”, assignments, and function calls) in code snippets.

    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
     pasien
    -0.92
     cantar
    -0.86
     seni
    -0.83
    KAN
    -0.82
     verbe
    -0.80
     durs
    -0.80
    Kan
    -0.78
     TAGS
    -0.77
    AVIS
    -0.76
     文件
    -0.76
    POSITIVE LOGITS
     Kriege
    0.91
    stimulus
    0.87
     πάν
    0.83
    ((
    0.83
     Anliegen
    0.81
     (((
    0.81
    =$
    0.81
     according
    0.79
     (!(
    0.78
     vegetación
    0.78
    Activations Density 0.003%

    No Known Activations