© 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. 31-GEMMASCOPE-2-RES-262K
    7. 201133
    Prev
    Next
    INDEX
    Explanations

    Tsukiji Outer Market

    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
    ми
    0.56
    WEATHER
    0.50
    йн
    0.49
    새
    0.49
    ة
    0.47
    Í
    0.47
    за
    0.46
    博
    0.46
    ция
    0.46
    ীর
    0.46
    POSITIVE LOGITS
     Education
    0.49
     Control
    0.48
     Communication
    0.48
     Roles
    0.46
     Metabolism
    0.45
     Diet
    0.45
     Eating
    0.45
     roles
    0.44
     Dance
    0.44
     Networking
    0.44
    Activations Density 0.002%

    No Known Activations