© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69175
    Prev
    Next
    INDEX
    Explanations

    orthopedic, identifiable, very

    np_acts-logits-general · gemini-2.5-flash-lite

    independent deployment and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ぐ
    0.53
     plays
    0.44
    ，
    0.44
     you
    0.42
     mys
    0.42
     womb
    0.42
     offs
    0.41
     myeloma
    0.41
     vers
    0.41
    ikum
    0.41
    POSITIVE LOGITS
    职务
    0.47
     Succeed
    0.46
     istit
    0.45
    证据
    0.45
     উচিৎ
    0.45
    ␶
    0.44
    ުގައި
    0.44
     एनसी
    0.44
    技术的
    0.44
    itação
    0.43
    Activations Density 0.003%

    No Known Activations