© 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. 40-GEMMASCOPE-2-RES-262K
    7. 27445
    Prev
    Next
    INDEX
    Explanations

    facing West or South

    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
     Eastern
    0.57
     vých
    0.56
     восто
    0.52
    Eastern
    0.52
     Восто
    0.48
     Southeastern
    0.46
     southeastern
    0.46
     동
    0.45
     southeast
    0.44
     راجس
    0.43
    POSITIVE LOGITS
     غرب
    0.75
     WEST
    0.74
     western
    0.73
     Western
    0.73
    Western
    0.72
     запад
    0.72
    西
    0.70
     Запа
    0.69
     西
    0.69
    西部
    0.69
    Activations Density 0.025%

    No Known Activations