© 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. 13241
    Prev
    Next
    INDEX
    Explanations

    days of the week and months

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

    The neuron primarily detects numeric tokens (especially years and numerical values).

    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
     fácil
    0.50
     incorporating
    0.49
     alb
    0.47
     приступи
    0.47
     ē
    0.47
     qualify
    0.47
     multi
    0.46
    spers
    0.45
     organiza
    0.45
     х
    0.45
    POSITIVE LOGITS
    বন্দ
    0.56
     sunday
    0.49
    Saturday
    0.48
    卧
    0.48
    ysteine
    0.48
    olate
    0.46
    เธอ
    0.46
    Sunday
    0.46
    不敢
    0.46
     रविवार
    0.45
    Activations Density 0.101%

    No Known Activations