© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7802
    Prev
    Next
    INDEX
    Explanations

    type parameters, primitive types, common data types

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

    The neuron fires on programming‐related identifier and type tokens (e.g. data‐type names like String, boolean, char, pointer symbols, field/ID names) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (**
    0.68
     (\<
    0.62
    жига
    0.61
     ›
    0.61
    彡
    0.59
    𝘵
    0.53
     (>
    0.52
    がございます
    0.51
     Certain
    0.50
     (<
    0.49
    POSITIVE LOGITS
    []
    3.92
     []
    3.33
    []=
    3.03
    [][]
    2.95
    [];
    2.92
    [],
    2.86
    [][
    2.81
    [])
    2.61
    []{
    2.47
     [][]
    2.45
    Activations Density 0.020%

    No Known Activations