© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31362
    Prev
    Next
    INDEX
    Explanations

    Middle Eastern languages

    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
    处于
    -0.90
     croix
    -0.86
    neho
    -0.82
    頻
    -0.79
    Thunk
    -0.77
    Lille
    -0.76
    lerim
    -0.75
    llä
    -0.74
    
    -0.72
    ῆς
    -0.72
    POSITIVE LOGITS
    Résumé
    0.78
    さり
    0.78
    قط
    0.78
     мощности
    0.75
     строе
    0.75
    âteau
    0.73
     մի
    0.73
     niya
    0.73
     ||
    0.73
    lup
    0.73
    Activations Density 0.005%

    No Known Activations