© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 118680
    Prev
    Next
    INDEX
    Explanations

    idermied, corvids, shrinking, cra, tile, cirrus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ب
    0.66
     been
    0.64
     desde
    0.59
    -‘
    0.57
     incessantly
    0.56
     we
    0.55
     penjualan
    0.55
    鳎
    0.55
     Συν
    0.54
    ’
    0.54
    POSITIVE LOGITS
    јан
    0.59
    ther
    0.57
    ٹن
    0.55
     تیم
    0.55
     روک
    0.55
     hysteria
    0.53
    ں
    0.53
    pharm
    0.52
    geometric
    0.52
    stationary
    0.52
    Activations Density 0.000%

    No Known Activations