© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30019
    Prev
    Next
    INDEX
    Explanations

    surface texture and roughness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     garb
    -0.70
     thái
    -0.70
     bền
    -0.68
     koe
    -0.68
     vận
    -0.68
     khởi
    -0.66
    辛
    -0.66
    🇭
    -0.65
    walla
    -0.65
    Gym
    -0.65
    POSITIVE LOGITS
     roughness
    2.16
     Rough
    1.64
    Rough
    1.39
     surface
    1.38
    rough
    1.34
     asper
    1.25
     profil
    1.25
     rough
    1.23
    surface
    1.23
     profile
    1.17
    Activations Density 0.054%

    No Known Activations