© 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. 224379
    Prev
    Next
    INDEX
    Explanations

    following website.com

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

    technical terms and concepts

    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
     여기에
    0.56
     편집
    0.50
    цией
    0.49
     আর্জেন্টিনা
    0.48
    妛
    0.48
     봉
    0.47
     타이
    0.47
    벼
    0.47
     অর্ধেক
    0.47
     만들어
    0.46
    POSITIVE LOGITS
    ’
    0.62
    laser
    0.57
    is
    0.56
    o
    0.55
    un
    0.55
    va
    0.54
     Laser
    0.52
    com
    0.52
    ž
    0.52
    a
    0.51
    Activations Density 0.000%

    No Known Activations