© 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. 5704
    Prev
    Next
    INDEX
    Explanations

    new List, new StringBuilder, new HashSet

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

    This neuron detects programming‐language code tokens, especially error‐throwing and object‐instantiation keywords (e.g. “throw,” “new,” runtime‐error messages).

    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
    new
    1.22
     new
    1.11
    新しい
    1.10
     새로운
    1.05
    Yeni
    1.02
    新
    1.02
     nieuwe
    1.01
    的新
    1.00
    新的
    0.99
     новые
    0.99
    POSITIVE LOGITS
     StringBuilder
    0.67
     seekBar
    0.65
     ();
    0.63
     கூறிய
    0.63
     medicare
    0.55
     fscanf
    0.55
     construed
    0.55
     golpe
    0.55
     atent
    0.54
     なく
    0.54
    Activations Density 0.003%

    No Known Activations