© 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. 14973
    Prev
    Next
    INDEX
    Explanations

    Separable convolutions

    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
     memperkenalkan
    0.55
    L
    0.51
    speople
    0.50
    people
    0.50
    tional
    0.48
    সকল
    0.47
    ovember
    0.46
    iexpress
    0.46
     डेली
    0.46
    ilize
    0.46
    POSITIVE LOGITS
    吕
    0.47
    汔
    0.47
     headsets
    0.47
    冎
    0.45
    穼
    0.45
     концерт
    0.44
     其
    0.44
     játék
    0.44
    িল্প
    0.43
    试验
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.