© 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. 6189
    Prev
    Next
    INDEX
    Explanations

    detectionapplicationAppendixaxis

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

    This neuron activates on numeric tokens and number-like expressions (e.g. digits, years, and decimal quantities).

    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
    გორ
    0.71
    ą
    0.68
    TIM
    0.66
    образ
    0.66
    RJ
    0.66
    Tu
    0.66
     gospel
    0.66
    Nos
    0.65
    ној
    0.64
     spoilers
    0.63
    POSITIVE LOGITS
    జేపీ
    0.84
    kannt
    0.77
     Unters
    0.75
     Wetter
    0.75
    ედერ
    0.74
    ု
    0.74
     Ironically
    0.73
     simpler
    0.72
    யோ
    0.71
     HO
    0.71
    Activations Density 0.000%

    No Known Activations