© 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. 151723
    Prev
    Next
    INDEX
    Explanations

    original positive meanings

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

    code, details, processing, distances

    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
     druga
    0.50
    辅助
    0.47
     पहला
    0.47
    地形
    0.47
    教会
    0.47
    蕉
    0.46
    Wasser
    0.46
    ể
    0.46
    之外
    0.45
    之间
    0.44
    POSITIVE LOGITS
     tweeted
    0.52
     नाबाद
    0.52
     unrelenting
    0.50
     populous
    0.50
     eighty
    0.50
     seventy
    0.49
     ninety
    0.49
     %.
    0.48
     yüzde
    0.46
     unscathed
    0.46
    Activations Density 0.001%

    No Known Activations