© 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. 189138
    Prev
    Next
    INDEX
    Explanations

    responsibilities and ensure

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

    london uk

    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
     الرئيسية
    0.61
     الكم
    0.51
    ند
    0.50
    frmt
    0.49
    دارة
    0.49
    欬
    0.49
    ندی
    0.48
    获得的
    0.48
    ವಾಗಿರುತ್ತದೆ
    0.47
    ኝ
    0.47
    POSITIVE LOGITS
    of
    0.50
    （
    0.48
     cambió
    0.48
     linux
    0.47
    R
    0.47
    oft
    0.46
    M
    0.45
    <sup>
    0.45
     changing
    0.44
    Lamb
    0.44
    Activations Density 0.000%

    No Known Activations