© 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. 9470
    Prev
    Next
    INDEX
    Explanations

    Please reach out

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

    The neuron strongly activates on numeric tokens—especially values like years, percentages, counts, and other standalone numbers.

    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
    u
    0.83
    ר
    0.81
    ו
    0.81
    نید
    0.80
    at
    0.78
    ल्या
    0.75
    zelfde
    0.75
     avions
    0.73
     statistique
    0.73
    quele
    0.72
    POSITIVE LOGITS
     когда
    0.80
     histamine
    0.80
     וב
    0.78
    $$
    0.77
     όταν
    0.77
     รู้
    0.74
     hurling
    0.74
    buatan
    0.73
     biochemical
    0.73
     ύ
    0.73
    Activations Density 0.001%

    No Known Activations