© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130928
    Prev
    Next
    INDEX
    Explanations

    tea

    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_10/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
    哂
    -2.05
    が欲しい
    -1.80
    ↵
    -1.67
    を設置
    -1.63
    quartier
    -1.55
    
    -1.55
    が無い
    -1.54
    
    -1.49
     painel
    -1.48
    を変更
    -1.46
    POSITIVE LOGITS
    مين
    1.78
    $
    1.62
     or
    1.57
     vienas
    1.56
    ☕️
    1.52
     類
    1.51
     jit
    1.46
    ☕
    1.45
     pirm
    1.44
    e
    1.44
    Activations Density 0.014%

    No Known Activations