© 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. 40-GEMMASCOPE-2-RES-262K
    7. 99657
    Prev
    Next
    INDEX
    Explanations

    large reptiles

    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_40_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
     bee
    0.41
    openzeppelin
    0.40
     bees
    0.40
    🥜
    0.39
     bumble
    0.39
    omag
    0.38
    DataFrame
    0.38
     pollin
    0.38
     सिख
    0.38
    ccin
    0.38
    POSITIVE LOGITS
     crocodile
    1.11
    鱷
    1.07
    🐊
    1.03
    鳄
    1.02
     crocodiles
    1.02
     Crocodile
    0.99
     alligator
    0.95
    crocodile
    0.88
     croc
    0.79
    鼍
    0.73
    Activations Density 0.020%

    No Known Activations