© 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. 34-GEMMASCOPE-RES-131K
    7. 38450
    Prev
    Next
    INDEX
    Explanations

    accented characters and symbols

    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
    ENESS
    -0.79
     droit
    -0.78
    ENCES
    -0.78
     式
    -0.76
    НЕ
    -0.75
     investors
    -0.75
     вред
    -0.75
    Dirty
    -0.73
    OMES
    -0.72
    νομα
    -0.71
    POSITIVE LOGITS
    <<(
    0.85
    ען
    0.77
    andale
    0.74
    そんな
    0.73
    NAH
    0.72
     lavoratori
    0.72
     l
    0.71
    
    0.71
     PPM
    0.70
    ǔ
    0.70
    Activations Density 0.007%

    No Known Activations