© 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. 9884
    Prev
    Next
    INDEX
    Explanations

    csharp code structure

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

    The neuron fires on numeric literals (e.g. version numbers, GUID values, floating‐point constants) embedded 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
     @
    0.63
     Rosenberg
    0.54
     /**
    0.54
    @
    0.54
     ROS
    0.54
    ✠
    0.52
     जल
    0.52
    ﻢ
    0.52
    @-
    0.51
     நீர்
    0.50
    POSITIVE LOGITS
    readonly
    0.66
     #[
    0.57
    +[
    0.54
     const
    0.54
     readonly
    0.54
     ଓ
    0.54
    лна
    0.52
     [\
    0.51
    勮
    0.51
    维度
    0.50
    Activations Density 0.000%

    No Known Activations