© 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. 1446
    Prev
    Next
    INDEX
    Explanations

    avoid doing

    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
     mutta
    -2.03
     zahlreichen
    -1.88
     But
    -1.87
    guigu
    -1.75
     birkaç
    -1.72
    䊐
    -1.66
     tačiau
    -1.62
    谖
    -1.62
     bisherigen
    -1.61
     Aufenthal
    -1.60
    POSITIVE LOGITS
     also
    1.75
    های
    1.70
     largeur
    1.66
    СКИ
    1.60
    ").
    1.60
    鸶
    1.54
     emma
    1.52
    脔
    1.52
     verhind
    1.52
     رعایت
    1.48
    Activations Density 0.004%

    No Known Activations