© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12078
    Prev
    Next
    INDEX
    Explanations

    lesson or task descriptions

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

    The neuron strongly activates on numeric tokens (years, page numbers, citation numbers, dates) typically found in titles, headings, or metadata.

    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
     Surg
    0.63
     경영
    0.60
    _{\
    0.58
    _{
    0.55
    onucle
    0.55
    MDP
    0.55
    osur
    0.55
    ОВ
    0.54
    orders
    0.54
    enschutz
    0.54
    POSITIVE LOGITS
     literalmente
    0.71
     literal
    0.65
     literally
    0.64
     शुक्रवार
    0.61
    酝
    0.61
     ലക്ഷ
    0.60
     सोमवार
    0.59
    점
    0.59
     வடக்கு
    0.58
     waist
    0.57
    Activations Density 0.000%

    No Known Activations