© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15819
    Prev
    Next
    INDEX
    Explanations

    including nuanced or major

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

    The neuron is specialized in detecting numeric figures—tokens representing numbers, measurements, statistics, or other quantified 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
     этом
    0.88
     двадцать
    0.81
    多い
    0.77
    öger
    0.77
     этой
    0.77
     бывает
    0.75
     живут
    0.75
     後
    0.75
     امرأة
    0.73
     второй
    0.71
    POSITIVE LOGITS
    DU
    0.80
    way
    0.73
    hi
    0.73
    tus
    0.72
     paced
    0.71
     tenue
    0.71
    torn
    0.70
     sustains
    0.70
    Si
    0.70
    を担当
    0.70
    Activations Density 0.000%

    No Known Activations