© 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. 143390
    Prev
    Next
    INDEX
    Explanations

    cleft palate, twin spar, ranges from, Argentavis

    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
    c
    0.73
    re
    0.56
    ис
    0.56
     ዕ
    0.54
    gou
    0.54
    ు
    0.54
     comprobar
    0.50
     onscreen
    0.50
    t
    0.50
    g
    0.50
    POSITIVE LOGITS
     %
    0.53
     ma
    0.51
     Prize
    0.50
     Grammar
    0.50
     kalo
    0.50
     Films
    0.49
     Consultancy
    0.48
     Kan
    0.48
     Senator
    0.48
     nari
    0.48
    Activations Density 0.000%

    No Known Activations