© 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. 12282
    Prev
    Next
    INDEX
    Explanations

    optional updates

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

    The neuron is keyed to recognize the “‐” or “-” dash character (e.g. leading hyphens).

    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
    @
    0.63
    Ｐ
    0.61
    oe
    0.61
    Analysis
    0.58
    ron
    0.57
    Script
    0.57
    battle
    0.56
    og
    0.55
    C
    0.55
    蜜
    0.55
    POSITIVE LOGITS
    Precio
    0.67
     grueso
    0.65
     equivalents
    0.64
     จริง
    0.63
     lɛ
    0.63
     கடன்
    0.62
     பகிர்ந்து
    0.62
     ราคา
    0.61
     odorless
    0.61
     Maß
    0.59
    Activations Density 0.249%

    No Known Activations