© 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. 9346
    Prev
    Next
    INDEX
    Explanations

    keep it simple

    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
     you
    -2.05
    甃
    -1.83
     Möglichkeit
    -1.75
     it
    -1.74
     garantir
    -1.70
    翾
    -1.70
     garantía
    -1.70
     militer
    -1.65
     they
    -1.63
    '';
    -1.63
    POSITIVE LOGITS
    ۥ
    1.64
    淦
    1.64
     iconic
    1.59
    しています
    1.57
     ethereal
    1.55
     Nichts
    1.54
    混乱
    1.53
    责任编辑
    1.52
    ：……
    1.52
    ’
    1.52
    Activations Density 0.012%

    No Known Activations