© 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. 12920
    Prev
    Next
    INDEX
    Explanations

    GRE registration exam

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

    This neuron detects the structured metadata headings and labels (especially capitalized field names and numeric entries) used in formal notices or job/examination announcements.

    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
     SPEAKER
    0.63
     Reactors
    0.62
    老板
    0.61
    CHAIN
    0.60
     प्रकल्
    0.60
    ⎣
    0.60
     அமிலம்
    0.58
     princesa
    0.58
    ụy
    0.58
    <unused35>
    0.57
    POSITIVE LOGITS
     admit
    0.77
    报考
    0.73
     exam
    0.69
     Admit
    0.69
     candidates
    0.68
     examination
    0.66
     examinations
    0.66
    考生
    0.66
     downloaded
    0.64
     exams
    0.64
    Activations Density 0.167%

    No Known Activations