© 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. 155945
    Prev
    Next
    INDEX
    Explanations

    princes of

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

    tea tray

    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
    ar
    0.48
    च
    0.46
    hi
    0.44
     virt
    0.43
    gle
    0.42
     soltanto
    0.42
     apert
    0.41
    确实
    0.41
    ₩
    0.41
     portals
    0.41
    POSITIVE LOGITS
    廢
    0.50
    Tabuleiro
    0.49
     επικ
    0.48
    iyê
    0.45
     Menteri
    0.45
     ছিলেন
    0.45
    ಿಸಿದ್ದ
    0.44
     Hiz
    0.44
     Ministère
    0.44
     Serra
    0.44
    Activations Density 0.000%

    No Known Activations