© 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. 16289
    Prev
    Next
    INDEX
    Explanations

    consecutive letters, API key, robots.txt

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

    This neuron activates on numeric tokens representing decimal numbers (i.e., floating‐point 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
    шире
    0.80
    렛
    0.78
    STATE
    0.72
    реди
    0.71
     पढ
    0.71
    Polynomial
    0.71
    ᆸ
    0.71
    гности
    0.70
    裡的
    0.70
    漼
    0.70
    POSITIVE LOGITS
    ,
    0.88
     proficient
    0.72
    :
    0.71
    ,}
    0.69
     tam
    0.68
     tamar
    0.68
    ym
    0.67
    ance
    0.66
     fans
    0.66
     pada
    0.66
    Activations Density 0.000%

    No Known Activations