© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15007
    Prev
    Next
    INDEX
    Explanations

    per share, acid, entity, perpendicular

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

    This neuron specializes in spotting numeric statistical results (e.g., p-values, odds ratios, confidence-interval figures) in scientific or medical text.

    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
    PubKey
    0.89
    Tanggal
    0.81
     przy
    0.81
    ק
    0.78
    secrets
    0.77
     ಮಾಡಿದ
    0.77
     uygulama
    0.77
    pap
    0.76
    𝔯
    0.76
    Khi
    0.75
    POSITIVE LOGITS
     encounters
    0.81
     acoustics
    0.78
     blooms
    0.74
     ounces
    0.73
     austerity
    0.73
     evaporation
    0.72
     interviews
    0.72
     entities
    0.71
     localities
    0.71
     Amherst
    0.71
    Activations Density 0.000%

    No Known Activations