© 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. 58598
    Prev
    Next
    INDEX
    Explanations

    puzzle and intricate patterns

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

    ratings, symbols, code

    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
    ジング
    0.51
     COUN
    0.46
     druge
    0.45
    в
    0.45
    နယ်
    0.45
     phim
    0.45
     RIGHTS
    0.44
    வர்
    0.44
    ्रेडिट
    0.44
     ontst
    0.44
    POSITIVE LOGITS
    Found
    0.43
    藠
    0.42
    Significant
    0.42
    ujian
    0.41
     Puzzle
    0.41
    Puzzle
    0.40
     розгля
    0.40
    Disk
    0.39
     magnitud
    0.39
    uisine
    0.39
    Activations Density 0.000%

    No Known Activations