© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14750
    Prev
    Next
    INDEX
    Explanations

    separators

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

    The neuron flags standout “keyword” tokens—that is, unusually informative or content-heavy words in the text.

    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
     deverá
    0.88
     belanja
    0.86
     dissipative
    0.86
    numOf
    0.85
    elementAt
    0.85
    총
    0.84
    기준
    0.83
    après
    0.80
    logne
    0.78
    BEAN
    0.78
    POSITIVE LOGITS
    ruh
    0.76
    ﺭ
    0.72
     いい
    0.67
    ৰ
    0.67
     ווא
    0.66
     Как
    0.66
     相
    0.66
     Игра
    0.66
     rings
    0.65
    ের
    0.65
    Activations Density 0.000%

    No Known Activations