© 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. 87088
    Prev
    Next
    INDEX
    Explanations

    static code constructs

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

    The neuron fires on programming‐language type names and declarations (e.g. “PyObject,” “struct,” “int,” “dispatch_once_t,” etc.).

    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
    新潟
    -0.86
    ış
    -0.82
     之
    -0.82
    ่านั้น
    -0.80
     Դ
    -0.79
    カタ
    -0.79
    lids
    -0.79
     bulk
    -0.77
    と
    -0.76
     they
    -0.75
    POSITIVE LOGITS
    once
    0.90
    एँ
    0.81
     uusi
    0.79
    GEAR
    0.79
     filles
    0.79
    película
    0.78
     once
    0.77
    来ました
    0.77
     kater
    0.76
     onlar
    0.76
    Activations Density 0.006%

    No Known Activations