© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63310
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    1.17
    is
    1.13
    d
    1.02
    기
    1.01
    ت
    1.00
    不
    0.95
    ع
    0.94
    고
    0.94
    ಬ್ಬಿಣ
    0.93
    el
    0.91
    POSITIVE LOGITS
    <0x80>
    0.96
    0
    0.85
    ;,
    0.82
    ૦
    0.82
    ى
    0.79
    ");
    0.78
     увеличи
    0.78
    `);
    0.77
    ).}
    0.77
    *}
    0.75
    Activations Density 0.128%

    No Known Activations