© 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. 30566
    Prev
    Next
    INDEX
    Explanations

    introducing specific details

    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
    <unused531>
    0.44
    Begriffsklär
    0.43
     ሌሎች
    0.42
    untza
    0.42
    <unused1115>
    0.42
    LabelTool
    0.41
     ?!
    0.41
    TreeNavigator
    0.41
    方も
    0.40
     وغيرها
    0.39
    POSITIVE LOGITS
    specifically
    0.63
     Specifically
    0.59
    Specifically
    0.56
    ي
    0.54
    ية
    0.52
    >
    0.50
    ки
    0.49
     específicamente
    0.48
     specifically
    0.48
    どのような
    0.48
    Activations Density 0.038%

    No Known Activations