© 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. 1624
    Prev
    Next
    INDEX
    Explanations

    function calls and definitions

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

    The neuron fires on capitalized technical identifiers (function or API names) in code‐like contexts.

    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
     britannique
    0.75
     trastornos
    0.71
     upholstered
    0.70
     corticoster
    0.69
     România
    0.68
     ໜອງ
    0.68
     ଏ
    0.68
     británico
    0.68
     regaining
    0.66
     那麼
    0.66
    POSITIVE LOGITS
    (
    1.41
    __(
    1.23
     (
    1.21
    ?(
    1.20
    ById
    1.17
    (@
    1.16
    (_,
    1.16
    (_
    1.13
    IfNeeded
    1.11
    ($
    1.10
    Activations Density 0.011%

    No Known Activations