© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13105
    Prev
    Next
    INDEX
    Explanations

    descriptive text following specific tokens

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

    This neuron fires strongly on tokens that begin a new sentence or paragraph break.

    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
    দেন
    0.80
     думаю
    0.79
     unborn
    0.78
    সম্যান
    0.74
    温柔
    0.74
     venom
    0.73
     equivalente
    0.73
    钀
    0.72
    அது
    0.72
     хозяйства
    0.71
    POSITIVE LOGITS
     배웠
    0.75
    രിച്ചി
    0.72
    정에
    0.71
    '"
    0.71
     지난
    0.70
     टूटा
    0.70
     이미지
    0.69
    ro
    0.69
     parlato
    0.67
     กร
    0.66
    Activations Density 0.000%

    No Known Activations