© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13964
    Prev
    Next
    INDEX
    Explanations

    java imports

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

    The neuron strongly responds to technical identifiers and code‐related names—e.g. library and class names, file‐path or URL path segments, and package or module identifiers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     javax
    0.64
    javax
    0.46
     java
    0.45
     Desenvolvimento
    0.41
     Calcula
    0.39
    诃
    0.39
    \/}
    0.39
    ческие
    0.38
    CRUD
    0.38
     век
    0.37
    POSITIVE LOGITS
    ;
    0.46
     extraordinaire
    0.37
    他们的
    0.37
     stimulus
    0.36
     epinephrine
    0.35
    ;.
    0.34
    濑
    0.34
     ब्राह्मण
    0.33
    donor
    0.33
     shared
    0.33
    Activations Density 0.001%

    No Known Activations