© 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. 2469
    Prev
    Next
    INDEX
    Explanations

    Kannada and Tamil film titles

    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
     المقال
    -0.92
     насеље
    -0.81
     மற்ற
    -0.78
     Ample
    -0.78
    setRotation
    -0.76
    ของคุณ
    -0.73
     palatable
    -0.72
    ඹ
    -0.71
     leden
    -0.71
    ски
    -0.71
    POSITIVE LOGITS
    ológicas
    0.94
    phans
    0.94
    
    0.92
    ulitis
    0.91
     Nee
    0.91
    
    0.90
    ateness
    0.90
    atism
    0.87
    itisation
    0.87
    وائ
    0.87
    Activations Density 0.019%

    No Known Activations