© 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. 15302
    Prev
    Next
    INDEX
    Explanations

    code structure

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

    This neuron activates on numerical references (e.g. digits, ordinals, measurements) 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_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
     Sacchar
    0.80
     버
    0.78
     Compt
    0.77
     컴
    0.77
     Chag
    0.73
     }"
    0.72
     escalating
    0.71
     정확
    0.70
     비
    0.70
     ယ
    0.70
    POSITIVE LOGITS
    sid
    0.92
    ía
    0.83
     pensado
    0.82
    と言う
    0.80
     impresión
    0.80
    ija
    0.79
    wał
    0.79
    رت
    0.78
     म्हण
    0.77
    ajemy
    0.77
    Activations Density 0.000%

    No Known Activations