© 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. 222133
    Prev
    Next
    INDEX
    Explanations

    run from

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

    phrases like trying to

    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
    chnung
    0.49
     С
    0.48
    hender
    0.46
    コマンド
    0.45
    Directory
    0.44
    empre
    0.44
     حسين
    0.44
    λέ
    0.43
    τρέ
    0.43
    ხ
    0.43
    POSITIVE LOGITS
     aastal
    0.55
    b
    0.54
    c
    0.51
     amacıyla
    0.51
     ith
    0.46
    ेश्च
    0.45
     omt
    0.45
    n
    0.45
     fron
    0.45
    ゎ
    0.45
    Activations Density 0.000%

    No Known Activations