© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81464
    Prev
    Next
    INDEX
    Explanations

    numbers and specific items

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

    religious, cat, watching

    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
     mudah
    0.54
     क्लीन
    0.52
     願い
    0.52
     yönetim
    0.50
     Казіно
    0.50
    💞
    0.49
     MP
    0.49
    ບໍ
    0.49
     lLoginID
    0.49
    IRCONIUM
    0.49
    POSITIVE LOGITS
    ائط
    0.46
    terr
    0.46
    jects
    0.45
     densities
    0.44
    s
    0.44
    {
    0.44
    decl
    0.44
    0.44
     updates
    0.43
    يف
    0.43
    Activations Density 0.000%

    No Known Activations