© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28055
    Prev
    Next
    INDEX
    Explanations

    color, sky, management, BC, Professionals

    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_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
    a
    0.49
     Christmas
    0.48
     edibles
    0.48
     Europeans
    0.46
     enjoy
    0.46
     enjoying
    0.46
    络
    0.45
     English
    0.45
     Breakfast
    0.45
    惚
    0.45
    POSITIVE LOGITS
    Ctx
    0.47
    사
    0.46
    風景
    0.44
    кура
    0.43
    وه
    0.43
    Lib
    0.42
    랫
    0.42
    Sunny
    0.41
    デザイン
    0.41
    ংস
    0.41
    Activations Density 0.002%

    No Known Activations