© 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. 137119
    Prev
    Next
    INDEX
    Explanations

    foreign language snippets

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

    await linked to other

    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
    ✅
    0.49
     ctypes
    0.46
     heps
    0.45
     Email
    0.44
    ✔
    0.44
    প
    0.43
     AFRICA
    0.42
    வார
    0.41
     email
    0.41
    ',{
    0.40
    POSITIVE LOGITS
     sơ
    0.48
    ेंशन
    0.46
     thuyền
    0.46
     කළ
    0.46
     가장
    0.46
     seag
    0.46
     নিয়ে
    0.45
    Conver
    0.45
     Kiến
    0.45
    ρι
    0.45
    Activations Density 0.000%

    No Known Activations