© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12147
    Prev
    Next
    INDEX
    Explanations

    DevOps, az, if, VS commands

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

    This neuron fires on Visual Studio configuration strings—especially registry key paths and version 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_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
    Club
    0.60
     باشگاه
    0.59
     تسم
    0.58
     الحم
    0.52
    വേ
    0.52
    RFQ
    0.52
    黼
    0.52
    CLUB
    0.51
     agrega
    0.51
     venire
    0.51
    POSITIVE LOGITS
     restore
    0.65
     '$(
    0.63
     restoration
    0.62
     restores
    0.61
    restore
    0.59
    '%(
    0.59
    ClCompile
    0.57
     korean
    0.57
    tensorflow
    0.57
    $(
    0.56
    Activations Density 0.015%

    No Known Activations