© 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. 187317
    Prev
    Next
    INDEX
    Explanations

    park, videos, network, malleable slab

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

    Clock or Push

    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
    Negative Logits
    >>(
    0.46
     مسجد
    0.46
    فران
    0.46
     statutory
    0.45
     councillors
    0.44
     counsell
    0.44
     principales
    0.44
    쫀
    0.44
     voix
    0.43
    combine
    0.43
    POSITIVE LOGITS
     TOW
    0.45
     Turismo
    0.43
     CARE
    0.42
     Warfare
    0.42
     Minecraft
    0.41
     siege
    0.41
     finisher
    0.41
     Force
    0.41
    育成
    0.41
     OpenGL
    0.41
    Activations Density 0.000%

    No Known Activations