© 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. 5934
    Prev
    Next
    INDEX
    Explanations

    block

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

    The neuron activates on numeric tokens or figures embedded in the 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_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
    '
    0.82
     pictured
    0.77
     banked
    0.73
     intricate
    0.68
     intricately
    0.68
    ř
    0.65
    琪
    0.65
    ix
    0.64
    ِّ
    0.64
     consequatur
    0.64
    POSITIVE LOGITS
    ;</
    0.73
    缺陷
    0.70
    い
    0.70
     ervoor
    0.68
    解决方法
    0.68
     మాత్ర
    0.67
     उन
    0.67
    formulario
    0.67
    别人的
    0.67
    στηκε
    0.66
    Activations Density 0.000%

    No Known Activations