© 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. 10-GEMMASCOPE-RES-131K
    7. 1738
    Prev
    Next
    INDEX
    Explanations

    poems, riddles, and lyrics

    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_10/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
    ܃
    -1.62
    เกง
    -1.55
    垢
    -1.48
    笮
    -1.43
    peño
    -1.43
    iläum
    -1.42
    ppelt
    -1.42
    Elaboración
    -1.40
    Preparazione
    -1.38
    udayaan
    -1.36
    POSITIVE LOGITS
     about
    1.71
     from
    1.70
     that
    1.60
     or
    1.48
    :“
    1.43
     Tonnen
    1.37
     now
    1.35
      
    1.34
     también
    1.34
    mathrm
    1.31
    Activations Density 0.029%

    No Known Activations