© 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. 66930
    Prev
    Next
    INDEX
    Explanations

    code identifiers and closing brackets

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

    This neuron activates on tokens inside method (especially constructor) parameter lists in code.

    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
     there
    -1.13
    bisoft
    -0.98
     too
    -0.97
    usually
    -0.91
     here
    -0.91
     både
    -0.90
    salm
    -0.88
     usual
    -0.88
    Väl
    -0.85
     amaç
    -0.85
    POSITIVE LOGITS
    :'/
    0.94
     hän
    0.93
    okes
    0.93
     хотите
    0.93
    ——”
    0.90
     you
    0.89
    मत
    0.87
    ALE
    0.86
    ale
    0.86
    uling
    0.85
    Activations Density 0.001%

    No Known Activations