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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17756
    Prev
    Next
    INDEX
    Explanations

    fish and sea creatures

    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_262k_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
    猞
    0.63
     الفرق
    0.53
    弇
    0.50
     справед
    0.46
    clu
    0.46
    芨
    0.45
     ৪৯
    0.45
     रणबीर
    0.44
    𒌷
    0.43
     земле
    0.43
    POSITIVE LOGITS
     fish
    1.70
    🐟
    1.38
     fishes
    1.36
    魚
    1.33
     Fish
    1.30
    🐠
    1.30
     ikan
    1.28
     FISH
    1.27
    鱼
    1.23
     मछली
    1.23
    Activations Density 0.055%

    No Known Activations