© 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. 73381
    Prev
    Next
    INDEX
    Explanations

    sports tournaments and games

    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
     jeweiligen
    -0.96
    搡
    -0.80
     ребенку
    -0.78
    Usually
    -0.77
     or
    -0.76
    ждане
    -0.76
     Även
    -0.75
    無法
    -0.75
    诧
    -0.75
    One
    -0.75
    POSITIVE LOGITS
    żd
    0.95
    acons
    0.90
    viä
    0.86
    celo
    0.81
    レーキ
    0.81
    kmäler
    0.80
     aguda
    0.80
    rieron
    0.80
     tournament
    0.79
     guesses
    0.79
    Activations Density 0.012%

    No Known Activations