© 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. 16-GEMMASCOPE-2-RES-262K
    7. 21145
    Prev
    Next
    INDEX
    Explanations

    carry or signify something

    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
    ت
    1.91
    л
    1.91
    ي
    1.77
    ع
    1.70
    ل
    1.56
    ми
    1.46
    ب
    1.45
    т
    1.44
    ル
    1.38
    по
    1.34
    POSITIVE LOGITS
     Bear
    1.30
    '
    1.17
     Bearing
    1.12
    1.09
     bear
    1.05
    ’
    1.04
    il
    0.96
    Bear
    0.95
     Bulletin
    0.93
     Management
    0.92
    Activations Density 0.005%

    No Known Activations