© 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. 8464
    Prev
    Next
    INDEX
    Explanations

    PARAMETER assignment

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

    The neuron lights up on very common, high-frequency tokens (e.g. “could,” “times,” “more,” “some,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     образу
    0.87
    看了
    0.85
     спи
    0.83
     nelle
    0.77
     Hurd
    0.77
     ро
    0.76
    Описание
    0.76
     historique
    0.76
     Assisted
    0.75
     環
    0.75
    POSITIVE LOGITS
    xq
    0.81
    xas
    0.80
     cristianos
    0.75
    fyp
    0.75
    常量
    0.74
    QCD
    0.73
    स्ताना
    0.73
    empuan
    0.72
     combatir
    0.72
    xima
    0.72
    Activations Density 0.000%

    No Known Activations