© 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. 1320
    Prev
    Next
    INDEX
    Explanations

    regulatory

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

    The neuron is primarily triggered by numeric tokens—digits and decimal 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
     др
    0.78
     نیز
    0.76
     ս
    0.73
     (`
    0.72
     вскоре
    0.72
     &/
    0.72
     (!
    0.71
     (~
    0.71
    :~
    0.70
     مزید
    0.68
    POSITIVE LOGITS
     ähm
    1.38
     uh
    1.17
     cuz
    1.12
     sogenannte
    1.09
     Gonna
    1.04
     sogenannten
    1.03
     äh
    1.02
     yeah
    1.01
    嗯
    1.01
     Yeah
    1.00
    Activations Density 0.067%

    No Known Activations