© 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. 22-GEMMASCOPE-RES-131K
    7. 95370
    Prev
    Next
    INDEX
    Explanations

    declaration and control flow

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

    This neuron fires on multi-word code identifiers written in camelCase (especially method names like ShouldOverrideUrlLoading or onKeyDown).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    CDP
    -0.88
     larges
    -0.86
    boxer
    -0.84
    ℞
    -0.84
    $;
    -0.83
    cll
    -0.81
    Rr
    -0.81
     بسته
    -0.80
    BX
    -0.80
     ;$
    -0.80
    POSITIVE LOGITS
    bool
    0.94
    stdbool
    0.94
    能否
    0.91
    boolean
    0.90
    能不能
    0.87
     precum
    0.84
     comune
    0.83
    Evet
    0.83
    ρων
    0.83
    stava
    0.82
    Activations Density 0.004%

    No Known Activations