© 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. 26363
    Prev
    Next
    INDEX
    Explanations

    schooling fish

    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
    嗥
    0.41
    撷
    0.41
     медве
    0.40
     Mountaine
    0.39
    БК
    0.39
    熊
    0.38
    鹰
    0.38
    #__
    0.37
    毛
    0.37
     Shia
    0.37
    POSITIVE LOGITS
     fishes
    1.30
     fish
    1.21
    魚
    1.05
    Fish
    1.04
    fish
    1.02
     Fishes
    1.01
    鱼
    1.01
     Fish
    1.00
    FISH
    0.91
     মাছ
    0.88
    Activations Density 0.007%

    No Known Activations