© 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. 5124
    Prev
    Next
    INDEX
    Explanations

    criteria and conditions

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

    red giant, resource allocation

    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
    ت
    0.52
    ่
    0.52
    ز
    0.48
    و
    0.47
    ซึ่ง
    0.47
    where
    0.46
     Translations
    0.46
    which
    0.46
    开
    0.44
     Calculate
    0.44
    POSITIVE LOGITS
    θηκαν
    0.54
     كات
    0.51
    ються
    0.50
     каса
    0.50
     оружи
    0.47
     dieron
    0.47
     ك
    0.46
    θηκε
    0.46
     człowie
    0.46
     않습니다
    0.46
    Activations Density 0.000%

    No Known Activations