© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8770
    Prev
    Next
    INDEX
    Explanations

    keywords for configuration or code

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

    This neuron fires on technical code tokens—especially configuration keys, function or variable names, and other programming identifiers.

    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_24_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
     洗
    0.31
     الاص
    0.29
     カット
    0.29
     Erschein
    0.29
     シュ
    0.29
     млрд
    0.29
    panelMenuList
    0.29
     Règles
    0.29
     Ген
    0.28
     각종
    0.28
    POSITIVE LOGITS
    _
    0.32
     specify
    0.31
     owners
    0.31
     commenters
    0.30
     owner
    0.30
     viewer
    0.30
    网友
    0.30
     only
    0.29
    In
    0.29
     creators
    0.29
    Activations Density 0.000%

    No Known Activations