© 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. 67805
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets

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

    This neuron responds to code tokens that are written in uppercase (often with underscores)—e.g. constants, macros, or special “dunder” method names.

    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
    <bos>
    -1.29
    <0xA3>
    -1.20
    
    -1.19
    も
    -1.18
    は
    -1.16
    Indust
    -1.14
    を
    -1.13
    ulose
    -1.07
    では
    -1.05
    特長
    -1.05
    POSITIVE LOGITS
    事を
    1.22
    為に
    1.17
     a
    1.16
    事に
    1.14
    際には
    1.13
    のですか
    1.08
     similaire
    1.06
    事が
    1.05
    ようです
    1.02
    部に
    1.02
    Activations Density 0.044%

    No Known Activations