© 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. 41-GEMMASCOPE-2-RES-262K
    7. 653
    Prev
    Next
    INDEX
    Explanations

    fish and fish-related terms

    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
    Not in Any Lists

    No Comments

    Negative Logits
     മിക
    0.56
     procé
    0.54
    ัติ
    0.52
    ૂર્ણ
    0.51
     élytres
    0.50
    칡
    0.50
     പ്രവർത്തന
    0.49
     năng
    0.48
    andidates
    0.48
    ব্লিউ
    0.48
    POSITIVE LOGITS
     fish
    2.23
     Fish
    1.95
    🐟
    1.87
    Fish
    1.82
     fishes
    1.78
    鱼
    1.77
    魚
    1.75
    fish
    1.73
     FISH
    1.71
     pescado
    1.65
    Activations Density 0.025%

    No Known Activations