© 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. 9211
    Prev
    Next
    INDEX
    Explanations

    qap after me

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

    The neuron fires most strongly on numeric tokens—i.e. standalone numbers, digits, or numeric codes.

    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
     ‎
    0.84
     esclusivamente
    0.81
     rudimentary
    0.80
     skateboarding
    0.80
     discretionary
    0.78
     gratification
    0.78
     steadfast
    0.77
     philanthropic
    0.77
     espírito
    0.77
     gastronom
    0.75
    POSITIVE LOGITS
     Ours
    1.03
     Again
    0.77
     Ceux
    0.77
     Ztg
    0.76
     L
    0.75
     Abroad
    0.75
     Amended
    0.75
     Италии
    0.75
     prepd
    0.74
    ﻌ
    0.74
    Activations Density 0.537%

    No Known Activations