© 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. 2311
    Prev
    Next
    INDEX
    Explanations

    explanation and code

    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
    entityManager
    0.38
    again
    0.37
    <?>
    0.37
    それで
    0.36
     Entities
    0.36
    matory
    0.35
    ኖች
    0.35
     Smiths
    0.35
     Bodies
    0.35
     बुन्देलखण्ड
    0.35
    POSITIVE LOGITS
     شرح
    0.40
    趣
    0.40
     copy
    0.38
     verbre
    0.37
     knot
    0.36
    誢
    0.36
     bash
    0.36
     أفضل
    0.36
     fid
    0.35
     geh
    0.35
    Activations Density 0.009%

    No Known Activations