© 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. 3799
    Prev
    Next
    INDEX
    Explanations

    program control flow keywords

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

    The neuron detects sentence‐final confirmation or permission markers—words like “correct” in a tag question or “よい” (“it may be…”) indicating permission or affirmation.

    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
    における
    0.63
    等方面
    0.58
    传感器
    0.53
     happenings
    0.52
    たちが
    0.50
    涉及
    0.50
    日在
    0.50
    romechanical
    0.48
     வழங்கும்
    0.48
    sensor
    0.47
    POSITIVE LOGITS
    ค่ะ
    0.86
     입니다
    0.86
    !!
    0.82
    합니다
    0.81
    !!!
    0.79
     :)
    0.78
    !
    0.78
     했습니다
    0.75
     합니다
    0.73
    입니다
    0.73
    Activations Density 0.038%

    No Known Activations