© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 4111
    Prev
    Next
    INDEX
    Explanations

    programming how-to guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ති
    2.71
    ഗണ
    2.66
    ático
    2.59
    ف
    2.57
    诌
    2.48
    ရား
    2.44
    ringa
    2.44
    ಷ
    2.43
    ồ
    2.40
    зонта
    2.37
    POSITIVE LOGITS
    sman
    3.00
    er
    2.70
    erche
    2.60
    ிட்ட
    2.44
    ்ட
    2.41
    ligence
    2.41
    asInstanceOf
    2.37
    onbury
    2.33
    تج
    2.32
    ાડ
    2.31
    Activations Density 0.059%

    No Known Activations