© 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. 34-GEMMASCOPE-RES-131K
    7. 63457
    Prev
    Next
    INDEX
    Explanations

    programming constructs and function arguments

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

    This neuron activates on type names and return-type specifiers in code (e.g. int, void, double, custom class or enum 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_34/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
    []
    -1.12
     [],
    -0.94
    []>
    -0.91
    [],
    -0.84
     beträ
    -0.82
     [])
    -0.82
     [],
    -0.81
    lia
    -0.78
    []
    -0.77
    []{
    -0.76
    POSITIVE LOGITS
    ?
    2.13
     Function
    1.46
    ?
    1.05
    ؟
    0.97
     FUNCTION
    0.89
    ?}
    0.87
    ?)
    0.87
    elfth
    0.85
    ({
    0.84
    menuhi
    0.82
    Activations Density 0.001%

    No Known Activations