© 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. 65815
    Prev
    Next
    INDEX
    Explanations

    function call

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

    The neuron fires on code tokens that name methods or properties when they’re being invoked or accessed (e.g. “split,” “querySelector,” bracket indexing, 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_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
    ţin
    -0.90
    žius
    -0.90
    BlockingQueue
    -0.87
     momentan
    -0.87
     realizarse
    -0.87
    蓠
    -0.86
    getOr
    -0.85
    kli
    -0.85
    ➨
    -0.85
    ulaires
    -0.84
    POSITIVE LOGITS
     it
    0.99
     any
    0.93
     having
    0.81
     welches
    0.79
     should
    0.77
    ảng
    0.77
    غيل
    0.77
    パク
    0.75
     SCHOL
    0.75
    なんだ
    0.74
    Activations Density 0.016%

    No Known Activations