© 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. 7854
    Prev
    Next
    INDEX
    Explanations

    organizations and news sources

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

    The neuron is triggered by numeric data in citations or statistics (especially floating‐point figures).

    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
    4
    0.59
    ସ
    0.57
     ==
    0.56
    carousel
    0.56
     welcome
    0.54
     olímp
    0.54
    welcome
    0.53
    ﺳ
    0.53
    听说
    0.52
    Resize
    0.50
    POSITIVE LOGITS
     estimates
    0.69
     기준
    0.66
     estimations
    0.64
     기준으로
    0.64
     রিপোর্ট
    0.62
     leurs
    0.61
     njihov
    0.60
     전문가
    0.59
     surveys
    0.58
     यांनी
    0.58
    Activations Density 0.068%

    No Known Activations