© 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. 117841
    Prev
    Next
    INDEX
    Explanations

    Anglo or Franco prefixes

    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
    事態
    -0.90
     him
    -0.87
     infidelity
    -0.83
    予告
    -0.82
    ensed
    -0.82
     anticipate
    -0.80
    Westfalen
    -0.76
     trạng
    -0.71
    Sens
    -0.69
    îtres
    -0.69
    POSITIVE LOGITS
    American
    0.94
     American
    0.90
    пон
    0.88
    american
    0.79
    INVALID
    0.78
     répondu
    0.75
     کمی
    0.75
    arrière
    0.74
    onian
    0.73
    phone
    0.72
    Activations Density 0.046%

    No Known Activations