© 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. 7762
    Prev
    Next
    INDEX
    Explanations

    coordinators, operators

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

    likelihood

    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
     Wanneer
    0.21
     ४
    0.20
     我們
    0.20
     ৪
    0.20
     þat
    0.20
     ð
    0.20
     ৫
    0.19
     Portanto
    0.19
     manglid
    0.19
     Итак
    0.19
    POSITIVE LOGITS
    нг
    0.16
    но
    0.16
    ле
    0.16
     specialized
    0.16
    ра
    0.15
    ρα
    0.15
    ก
    0.15
    ри
    0.15
    ח
    0.15
    worldwide
    0.15
    Activations Density 0.554%

    No Known Activations