© 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. 14585
    Prev
    Next
    INDEX
    Explanations

    to determine

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

    The main thing this neuron does is spot numeric tokens and quantity/statistic mentions (numbers, percentages, years, large numeric values).

    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
     作業
    0.73
     Matters
    0.66
    に合わせて
    0.66
     مبنی
    0.64
     将
    0.63
    All
    0.63
    OM
    0.63
     系列
    0.63
     所有
    0.63
    Working
    0.62
    POSITIVE LOGITS
     récentes
    0.77
     weltweit
    0.75
     devido
    0.72
     vznik
    0.72
     its
    0.72
     debido
    0.71
     létre
    0.71
     occurs
    0.70
     его
    0.68
    牠
    0.68
    Activations Density 0.707%

    No Known Activations