© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13007
    Prev
    Next
    INDEX
    Explanations

    occur or occur during

    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
    蠖
    -2.19
    ᯾
    -2.19
    秕
    -2.08
     ſta
    -1.95
    seven
    -1.88
    Ꭳ
    -1.87
    
    -1.76
    乄
    -1.76
    ORIES
    -1.75
    橚
    -1.75
    POSITIVE LOGITS
     in
    2.45
     But
    1.87
    鋆
    1.85
    ◛
    1.73
     with
    1.59
    瑧
    1.59
     trän
    1.55
    ↵
    1.55
     noteworthy
    1.53
     What
    1.52
    Activations Density 0.035%

    No Known Activations