© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71122
    Prev
    Next
    INDEX
    Explanations

    event handling and identifiers

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

    The neuron fires strongly on code tokens that control event propagation (e.g. “bubble” and “stop”).

    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
    幛
    -1.30
     Rät
    -1.23
     utilización
    -1.23
    ➡️
    -1.20
    ⁛
    -1.19
    ور
    -1.16
    laması
    -1.15
     Ș
    -1.14
    絰
    -1.14
    ğine
    -1.13
    POSITIVE LOGITS
    ,”
    1.40
     tireless
    1.30
     valiant
    1.23
    s
    1.21
    整個
    1.21
     erratic
    1.20
    (),
    1.19
    両方
    1.19
    もとも
    1.18
     chug
    1.18
    Activations Density 0.001%

    No Known Activations