© 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. 124672
    Prev
    Next
    INDEX
    Explanations

    foreign characters and symbols

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

    can help

    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
    ا
    0.57
    的其他
    0.51
    اط
    0.49
    U
    0.48
    ح
    0.47
    اف
    0.46
    EG
    0.46
    IDEA
    0.46
    ZW
    0.44
    EPS
    0.43
    POSITIVE LOGITS
    ᐈ
    0.52
    vá
    0.51
    ká
    0.50
     ₽
    0.50
    írus
    0.50
    kara
    0.48
     exorbit
    0.47
     가는
    0.47
    ín
    0.46
     खांसी
    0.46
    Activations Density 0.004%

    No Known Activations