© 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. 93770
    Prev
    Next
    INDEX
    Explanations

    player number

    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
    спорта
    -0.74
     Bartlett
    -0.73
    Ɖ
    -0.72
     Peacock
    -0.71
    tiskt
    -0.71
    programma
    -0.71
    gero
    -0.70
    Vice
    -0.69
    Ɉ
    -0.69
    ️⃣
    -0.68
    POSITIVE LOGITS
     five
    1.05
     Five
    0.90
     пяти
    0.87
     Fünf
    0.85
     формате
    0.85
    Five
    0.79
     aside
    0.79
    empêcher
    0.79
     sides
    0.77
     kecil
    0.75
    Activations Density 0.021%

    No Known Activations