© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 58582
    Prev
    Next
    INDEX
    Explanations

    raw meat, carp, ceviche, sashimi

    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
     breakage
    0.47
    破
    0.45
    Ҭ
    0.41
    ্বক
    0.40
    ۸
    0.40
     கரி
    0.39
    
    0.38
    Equations
    0.38
    🔼
    0.37
    
    0.37
    POSITIVE LOGITS
     sashimi
    0.94
     carp
    0.85
    Carp
    0.76
     Carp
    0.76
     raw
    0.74
     Carn
    0.72
     RAW
    0.71
     car
    0.70
     cev
    0.70
    carn
    0.69
    Activations Density 0.005%

    No Known Activations