© 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. 9440
    Prev
    Next
    INDEX
    Explanations

    essay outline criticism

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

    This neuron detects numeric reference markers in bibliographic citations, such as volume numbers, page ranges, years, and other numeric identifiers.

    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
    en
    0.70
    im
    0.69
    hij
    0.64
     M
    0.62
    |
    0.61
    ra
    0.61
     S
    0.59
    封装
    0.59
     VW
    0.59
    cstring
    0.59
    POSITIVE LOGITS
     അല്ലെങ്കിൽ
    0.80
     như
    0.78
     rằng
    0.77
     endangering
    0.73
     đến
    0.71
     với
    0.70
     bolstering
    0.69
     quyển
    0.67
    珽
    0.66
     ぐらい
    0.65
    Activations Density 0.001%

    No Known Activations