© 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. 66137
    Prev
    Next
    INDEX
    Explanations

    Panama and related words

    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
     bậc
    -0.81
     UNAM
    -0.78
     ApiException
    -0.77
     TextStyle
    -0.74
     مي
    -0.73
     carlo
    -0.73
     snag
    -0.73
     AVI
    -0.72
     Devonshire
    -0.72
    мии
    -0.71
    POSITIVE LOGITS
     voorkomen
    0.77
     confiance
    0.67
    cea
    0.66
     Tom
    0.66
    {{\
    0.66
     wavy
    0.65
     Mike
    0.65
     organismos
    0.65
     proposition
    0.65
    
    0.64
    Activations Density 0.032%

    No Known Activations