© 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. 183987
    Prev
    Next
    INDEX
    Explanations

    foreign languages or multilingual contexts

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

    operations, grouping, repetition, and items

    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
     SDS
    0.54
    listFiles
    0.54
     ス
    0.48
    PSS
    0.47
    ミ
    0.46
    IFS
    0.45
    のス
    0.45
    ogloss
    0.45
     ච
    0.44
    ステ
    0.44
    POSITIVE LOGITS
     gjort
    0.41
    শিয়ার
    0.40
     itineraries
    0.39
     তাহাই
    0.38
    lett
    0.38
    inition
    0.38
     erwartet
    0.38
    issance
    0.38
     frontiers
    0.37
    нную
    0.37
    Activations Density 0.002%

    No Known Activations