© 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. 251132
    Prev
    Next
    INDEX
    Explanations

    properties, container, Barbados

    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
    ueve
    0.50
     পাচ
    0.48
    six
    0.47
    \">\
    0.46
    five
    0.46
    hop
    0.46
     установка
    0.46
    ’
    0.46
     congest
    0.45
    ACIÓN
    0.45
    POSITIVE LOGITS
    நாள்
    0.54
    酲
    0.49
    ел
    0.47
    酈
    0.47
    াকি
    0.46
    瘓
    0.45
     réal
    0.45
    ак
    0.45
    利率
    0.44
    ుడు
    0.43
    Activations Density 0.000%

    No Known Activations