© 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. 106040
    Prev
    Next
    INDEX
    Explanations

    This item can be shipped

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

    Increased Chinese military activity

    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
    𝚞
    0.48
    Ан
    0.47
     डायरेक्टर
    0.47
    ӯ
    0.47
    Петер
    0.46
    Пла
    0.46
    imètre
    0.46
     mismos
    0.46
     gubern
    0.45
    Ду
    0.45
    POSITIVE LOGITS
    用於
    0.50
    ENABLED
    0.48
    FED
    0.47
    REF
    0.45
    
    0.45
    Rotatef
    0.44
    神器
    0.43
    শোধ
    0.43
     গুরুতর
    0.42
    了不少
    0.42
    Activations Density 0.001%

    No Known Activations