© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10539
    Prev
    Next
    INDEX
    Explanations

    determinism and determining

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

    This neuron detects mentions of exams or examinations.

    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
    மதி
    0.63
    superior
    0.63
    ва
    0.61
    뾰
    0.61
    hw
    0.59
    لة
    0.59
     თქვენ
    0.59
    arming
    0.59
     función
    0.58
    <unused52>
    0.58
    POSITIVE LOGITS
    Ine
    0.79
     examiners
    0.78
     Examiners
    0.73
     Examine
    0.73
     Examiner
    0.72
     examiner
    0.68
     examine
    0.68
     Exam
    0.63
     Examination
    0.63
    考
    0.61
    Activations Density 0.036%

    No Known Activations