© 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. 80773
    Prev
    Next
    INDEX
    Explanations

    gift ideas and prizes

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

    foreign language phrases

    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
    ри
    0.53
    すべて
    0.47
    ोप
    0.47
    ೋಪ
    0.46
    ─
    0.45
     creatividad
    0.45
     PROTECTION
    0.44
     libertà
    0.44
    सन
    0.44
    OPER
    0.44
    POSITIVE LOGITS
    otá
    0.50
     మహిళ
    0.48
    额
    0.48
     쪽
    0.47
    mming
    0.46
     ခု
    0.46
    ifico
    0.46
     মানে
    0.45
     పై
    0.45
    ekkür
    0.44
    Activations Density 0.001%

    No Known Activations