© 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. 6838
    Prev
    Next
    INDEX
    Explanations

    javascript and python code snippets

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

    The neuron detects the names of server‐side middleware or database modules (e.g. connect-mongo, cookie-parser, express, mongoose, etc.).

    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
    曝
    0.62
    曝光
    0.60
    Ад
    0.60
    LOGO
    0.57
    题材
    0.57
    โห
    0.56
    Cherry
    0.55
    나무
    0.54
    年月日
    0.54
    字
    0.54
    POSITIVE LOGITS
     indexRouter
    0.71
     OPS
    0.64
     cors
    0.62
    ార్
    0.60
     సాధ
    0.55
     swimmers
    0.55
     wrestlers
    0.54
     lucha
    0.52
     maint
    0.52
     आठ
    0.52
    Activations Density 0.005%

    No Known Activations