© 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. 6222
    Prev
    Next
    INDEX
    Explanations

    Emoji and code/links

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

    The neuron detects asterisks used as footnote or reference markers.

    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
    ฟ้า
    0.60
    Evet
    0.55
    Від
    0.52
    Así
    0.52
     ฟ้า
    0.52
    От
    0.51
    폈
    0.50
    håll
    0.50
    .
    0.50
    <0xD1>
    0.50
    POSITIVE LOGITS
     Our
    0.49
     Languages
    0.46
     We
    0.46
     Kabupaten
    0.46
     rangkaian
    0.46
     jaringan
    0.46
     Regions
    0.45
     N
    0.45
     Lesotho
    0.45
     A
    0.45
    Activations Density 0.001%

    No Known Activations