© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12069
    Prev
    Next
    INDEX
    Explanations

    get/parse/sha/acquire/deserialize

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

    This neuron fires on the opening angle-bracket of generic type annotations (e.g. the “<” in “Observable<Status>”).

    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
     computable
    0.66
     BOOL
    0.63
     perror
    0.62
     કરતી
    0.57
     dataset
    0.56
     parallelogram
    0.56
    훑
    0.56
     curved
    0.56
    יים
    0.56
    :'',
    0.53
    POSITIVE LOGITS
    лимпий
    0.63
     consigo
    0.60
    abhavena
    0.60
     оставить
    0.58
    理
    0.58
    卸
    0.57
    Personal
    0.57
    恃
    0.56
    留下
    0.55
    ضمن
    0.55
    Activations Density 0.000%

    No Known Activations