© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 103748
    Prev
    Next
    INDEX
    Explanations

    slope, elevation, or terrain type

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     curvatures
    0.52
     curve
    0.46
     curvature
    0.46
     curved
    0.46
    曲线
    0.45
     curving
    0.45
     forests
    0.45
    擇
    0.45
     curv
    0.45
     Curved
    0.44
    POSITIVE LOGITS
    正
    0.53
     grade
    0.42
     away
    0.42
     Drop
    0.41
     falls
    0.40
     GRADE
    0.40
     Detroit
    0.39
     grades
    0.39
     TB
    0.38
    grade
    0.38
    Activations Density 0.000%

    No Known Activations