© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22114
    Prev
    Next
    INDEX
    Explanations

    HEK293 cells, gland

    np_acts-logits-general · gemini-2.5-flash-lite

    brand names, scientific terms, and specialized technical terminology.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    おわりに
    -2.08
    鹩
    -2.06
    橚
    -1.95
     indiví
    -1.88
    ᛬
    -1.88
    っかり
    -1.84
    ⚋
    -1.79
    蹌
    -1.78
    
    -1.77
    瑆
    -1.77
    POSITIVE LOGITS
     They
    2.16
    .
    1.95
     The
    1.80
     effortless
    1.72
     emotion
    1.70
      
    1.70
     At
    1.65
     personalmente
    1.65
    蜗
    1.64
     What
    1.60
    Activations Density 0.014%

    No Known Activations