© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 40587
    Prev
    Next
    INDEX
    Explanations

    J. Biol. Chem. or Housewives

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

    scientific and technical terminology, particularly chemistry terms and boxing/sports weight classes.

    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
    ܃
    -1.88
    
    -1.64
    Wymiary
    -1.61
     Проци
    -1.60
    ་་
    -1.57
    手掌
    -1.52
     {
    
    
    -1.50
     belo
    -1.50
    '):
    -1.47
    asztal
    -1.46
    POSITIVE LOGITS
    蘼
    1.79
    mathrm
    1.77
    และ
    1.53
    .”
    1.52
     of
    1.49
    ]
    1.49
     caratteri
    1.48
    <b>
    1.48
     либо
    1.48
    祼
    1.47
    Activations Density 0.028%

    No Known Activations