© 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. 10098
    Prev
    Next
    INDEX
    Explanations

    Hungry generation, HAMLET, Pierra Menta, Krakatoa

    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
     to
    -2.13
    ↵↵
    -2.08
     and
    -1.88
     is
    -1.82
     will
    -1.62
     in
    -1.52
     has
    -1.48
    lognese
    -1.45
    ATIVA
    -1.42
     of
    -1.39
    POSITIVE LOGITS
     ongles
    1.76
     énorm
    1.58
     solides
    1.56
     êtres
    1.54
     dépla
    1.53
     groupes
    1.52
     verring
    1.48
     grecque
    1.48
     potenci
    1.48
     clô
    1.47
    Activations Density 13.824%

    No Known Activations