© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 55574
    Prev
    Next
    INDEX
    Explanations

    names ending in uk/uck

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indari
    -0.80
    ajas
    -0.73
     Tones
    -0.71
     Trails
    -0.70
    闍
    -0.69
     ファイル
    -0.69
     dựng
    -0.69
    üht
    -0.68
     anzeigen
    -0.68
     widely
    -0.68
    POSITIVE LOGITS
    Ranks
    0.75
     بلکه
    0.75
    ै
    0.73
    mobile
    0.72
    dedu
    0.69
    дой
    0.69
     革
    0.68
    asInstanceOf
    0.68
     Semp
    0.67
    mediately
    0.66
    Activations Density 0.016%

    No Known Activations