© 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. 2791
    Prev
    Next
    INDEX
    Explanations

    reboot or steps

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

    The main thing this neuron does is detect tokens representing numeric references—years, page or verse numbers, and similar citation figures.

    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
     Моло
    0.53
    okat
    0.52
     παν
    0.51
     dotyczące
    0.51
    铂
    0.48
    ਵੇਂ
    0.48
     වන්නේ
    0.48
     کرتی
    0.47
    েমস
    0.47
    氓
    0.47
    POSITIVE LOGITS
    แส
    0.53
    shoz
    0.53
    riek
    0.51
     dihar
    0.51
    ائز
    0.49
    除此之外
    0.48
     ప్రారం
    0.48
    ^
    0.46
    Ἑ
    0.46
     accords
    0.46
    Activations Density 0.396%

    No Known Activations