© 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. 27200
    Prev
    Next
    INDEX
    Explanations

    declarations with static

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

    This neuron fires on C/C++ code declarations and directives (e.g. lines beginning with “#include” or keywords like “static” and “const”).

    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
     délicieux
    -1.34
    ⟡
    -1.20
    잘
    -1.20
     ideales
    -1.16
     {
    -1.16
     ouver
    -1.14
     ܕ
    -1.13
     tarea
    -1.13
     logiciel
    -1.12
     pelig
    -1.11
    POSITIVE LOGITS
     only
    1.12
    9
    1.08
    ,
    1.07
    [
    1.07
    5
    1.06
     can
    1.01
    7
    0.98
     with
    0.98
    i
    0.96
     has
    0.96
    Activations Density 0.002%

    No Known Activations