© 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. 92341
    Prev
    Next
    INDEX
    Explanations

    small amounts

    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
     הרבה
    -1.02
     gioielli
    -0.94
     meisje
    -0.93
     molte
    -0.92
     direttamente
    -0.90
     heerlijk
    -0.87
     bekende
    -0.87
     großes
    -0.84
     μεγά
    -0.84
     banyak
    -0.84
    POSITIVE LOGITS
     slight
    4.16
     small
    4.09
     minor
    3.83
     неболь
    3.69
    small
    3.19
    เล็ก
    3.17
     slightly
    3.09
     tiny
    3.03
     pequeñas
    2.92
    minor
    2.84
    Activations Density 0.210%

    No Known Activations