© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3800
    Prev
    Next
    INDEX
    Explanations

    date cutoff

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

    The neuron activates on occurrences of precise numeric values (especially decimals and percentages) 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
     límites
    0.87
    s
    0.73
    ização
    0.71
     voltam
    0.70
    ته
    0.70
    pare
    0.70
     taz
    0.70
    Calcul
    0.69
    นาย
    0.69
    calcul
    0.68
    POSITIVE LOGITS
     丨
    0.92
    ıll
    0.90
    ık
    0.88
    ında
    0.83
    ları
    0.82
    dır
    0.79
    👯
    0.79
     \|
    0.76
     EDITION
    0.75
    的是
    0.75
    Activations Density 0.000%

    No Known Activations