© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11995
    Prev
    Next
    INDEX
    Explanations

    complex variety alter create

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

    This neuron activates on bibliographic‐style metadata (download notices, dates, citations, URLs, and similar reference tokens).

    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
     buildFor
    0.78
     Registrar
    0.77
    UILLER
    0.76
    PEND
    0.75
    ਿਕ
    0.74
    т
    0.74
    ิ
    0.74
    ApiModel
    0.73
    isman
    0.73
    枉
    0.73
    POSITIVE LOGITS
     raio
    0.75
     Kø
    0.75
    abble
    0.75
     claro
    0.73
    ATES
    0.68
    ছাড়া
    0.67
    शाली
    0.66
     میر
    0.65
     coro
    0.65
     SLAs
    0.62
    Activations Density 0.000%

    No Known Activations