© 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. 53-GEMMASCOPE-2-RES-262K
    7. 87247
    Prev
    Next
    INDEX
    Explanations

    climb and climbing

    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/layer_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    鸨
    0.42
     پیس
    0.40
    撅
    0.39
    RoundRect
    0.38
    滬
    0.37
    沣
    0.37
     hydrogenation
    0.37
     hypersurface
    0.37
     Grosso
    0.37
    waitForIdleSync
    0.36
    POSITIVE LOGITS
     climbing
    3.80
     climb
    3.75
     climbed
    3.58
     climbs
    3.50
     Climbing
    3.42
     Climb
    3.34
     climbers
    3.28
     climber
    3.22
    攀
    2.56
     Clim
    2.44
    Activations Density 0.037%

    No Known Activations