© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49216
    Prev
    Next
    INDEX
    Explanations

    tea bags

    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_16_width_262k_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
    忽然
    0.53
    Trước
    0.51
    ശ
    0.50
    வு
    0.48
    升级
    0.48
    ቈ
    0.48
     ගැන
    0.47
    のス
    0.47
    ያንዳ
    0.47
    ጇ
    0.47
    POSITIVE LOGITS
    ↵
    0.64
    s
    0.64
    es
    0.61
    at
    0.60
    as
    0.57
     Modeling
    0.57
    y
    0.55
    ↵↵
    0.54
    al
    0.54
    is
    0.53
    Activations Density 0.000%

    No Known Activations