© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6721
    Prev
    Next
    INDEX
    Explanations

    dictionary or list containing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     использует
    0.71
     merciless
    0.70
     hamburger
    0.70
    consciously
    0.69
     Display
    0.69
    鸢
    0.67
    ด้าน
    0.67
     usa
    0.67
     caminar
    0.65
     ماشي
    0.65
    POSITIVE LOGITS
    }
    0.73
    ^{
    0.70
    prüng
    0.69
     Schlüssel
    0.67
    zaam
    0.64
    ressione
    0.63
    టే
    0.63
    clid
    0.62
    ότερα
    0.62
    擘
    0.62
    Activations Density 0.059%

    No Known Activations