© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11203
    Prev
    Next
    INDEX
    Explanations

    courtship and suitors

    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
    ↵
    -1.73
    !)
    -1.46
    一闪
    -1.39
     mại
    -1.35
    на
    -1.34
    ку
    -1.33
    !】
    -1.29
     removes
    -1.29
    ・「
    -1.28
     stil
    -1.27
    POSITIVE LOGITS
     each
    1.63
     zahr
    1.55
    鏷
    1.51
    
    1.44
     podla
    1.34
     nouveaux
    1.33
    瓛
    1.32
     nieuwe
    1.31
     šed
    1.30
     avulla
    1.30
    Activations Density 0.020%

    No Known Activations