© 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. 113394
    Prev
    Next
    INDEX
    Explanations

    foreign language characters and events

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

    circumstances

    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
    多的
    0.45
     smokes
    0.43
    ark
    0.42
    ို
    0.42
     realizing
    0.42
     န
    0.42
     hali
    0.42
    overlapping
    0.41
     যুদ্ধ
    0.41
     forty
    0.41
    POSITIVE LOGITS
    ToBe
    0.57
    Бе
    0.48
     וא
    0.47
    दुल
    0.47
    Santo
    0.47
    𝑰
    0.47
    燎
    0.46
     любом
    0.46
    身上
    0.46
    Здравствуйте
    0.45
    Activations Density 0.001%

    No Known Activations