© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 51717
    Prev
    Next
    INDEX
    Explanations

    skiing and related activities

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bedkar
    0.46
    문제
    0.42
     Routine
    0.40
     faucet
    0.40
    狱
    0.40
     बाथरूम
    0.39
     Wesleyan
    0.39
    备
    0.38
    setRequest
    0.38
     Ashok
    0.38
    POSITIVE LOGITS
     skiers
    1.30
     ski
    1.30
     skier
    1.29
     skiing
    1.28
     Ski
    1.12
     skis
    1.09
    ⛷
    1.09
    🎿
    1.00
     snowboard
    0.94
    スキー
    0.92
    Activations Density 0.037%

    No Known Activations