© 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. 172252
    Prev
    Next
    INDEX
    Explanations

    elephants, tonight, pick, State

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

    UI and language processing

    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
    ة
    0.57
    ing
    0.47
    价格
    0.46
     barato
    0.45
     कीमत
    0.44
    ustible
    0.44
    ຈ
    0.44
    远处
    0.43
    串口
    0.43
    et
    0.43
    POSITIVE LOGITS
    Зна
    0.49
    엮
    0.44
    radiative
    0.44
    ୟ
    0.43
     характеризу
    0.43
    utzen
    0.42
    <unused979>
    0.42
     проекты
    0.42
    кен
    0.41
    ⁉
    0.41
    Activations Density 0.001%

    No Known Activations