© 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. 6363
    Prev
    Next
    INDEX
    Explanations

    "):

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

    The neuron strongly activates on punctuation and delimiter symbols in code snippets—e.g. parentheses, colons, equals signs, backslashes—marking code‐style syntax.

    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
    兩個
    0.68
    四个
    0.64
    ２
    0.61
    三個
    0.59
    做法
    0.57
    पांच
    0.55
    ​
    0.54
    两个
    0.54
    ３
    0.54
    五个
    0.53
    POSITIVE LOGITS
     \""
    0.85
     ビタミン
    0.81
     さらに
    0.75
     ハート
    0.75
     {:.
    0.74
     ранее
    0.72
    aría
    0.71
    isesti
    0.71
     Trebuie
    0.71
     #{
    0.70
    Activations Density 0.000%

    No Known Activations