© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15876
    Prev
    Next
    INDEX
    Explanations

    check function call

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

    The neuron selectively activates on tokens that appear in TypeScript type/interface declarations (e.g. “export,” “interface,” “extends,” type names, the “>” generic marker, and the “{}” type braces).

    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
    vertissement
    -0.85
    replica
    -0.84
     minOccurs
    -0.81
    raujo
    -0.79
     největ
    -0.79
    Atlético
    -0.79
    過程中
    -0.78
    让我
    -0.77
     Befe
    -0.76
    Daha
    -0.75
    POSITIVE LOGITS
     acela
    0.90
     same
    0.87
     often
    0.84
     getAccount
    0.83
     aynı
    0.83
     shorthand
    0.81
    ▬▬
    0.80
    ()<<
    0.79
    wydd
    0.78
    通
    0.78
    Activations Density 0.017%

    No Known Activations