© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219224
    Prev
    Next
    INDEX
    Explanations

    venerating sapphires

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

    requires careful checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nowoczes
    0.53
    s
    0.51
     toujours
    0.50
     zawsze
    0.50
    à
    0.48
     extrémité
    0.46
    always
    0.46
     wonderfully
    0.46
    rs
    0.45
     нравится
    0.45
    POSITIVE LOGITS
     ginseng
    0.48
     vagin
    0.43
     Congreso
    0.43
     Конгре
    0.42
    锑
    0.42
     ప్రజా
    0.41
     PLANTS
    0.40
     tannin
    0.40
     البحث
    0.40
     PDA
    0.39
    Activations Density 0.001%

    No Known Activations