© 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. 37845
    Prev
    Next
    INDEX
    Explanations

    Banach, Polish, Stein, Borel spaces

    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
    curité
    -0.75
    barcode
    -0.74
     thua
    -0.74
     '\\;'
    -0.73
     Constantine
    -0.71
    Cooking
    -0.70
    VisualStyle
    -0.69
    cooking
    -0.69
    quilla
    -0.69
     gebe
    -0.68
    POSITIVE LOGITS
     Ba
    0.87
    Haar
    0.82
    Polish
    0.76
     Polish
    0.75
     Lakeside
    0.75
     met
    0.73
     Banach
    0.73
    ポー
    0.73
     descriptive
    0.70
    Ba
    0.70
    Activations Density 0.062%

    No Known Activations