© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68196
    Prev
    Next
    INDEX
    Explanations

    Lincolnshire, palsy, TCM

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

    medical conditions and disorders with suffixes like "-itis", "-ness", "-osis", and "-palsy".

    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
    臜
    -2.58
    龗
    -2.45
    
    -2.33
     گیری
    -2.27
     diesem
    -2.19
    ではなく
    -2.09
     verrou
    -2.09
    </h1>
    -2.05
    揾
    -2.02
    媗
    -2.02
    POSITIVE LOGITS
    </em>
    3.13
    ↵↵
    2.52
    “
    2.34
    </strong>
    2.13
    ly
    2.09
     obeying
    2.09
    ’
    2.00
     值
    1.95
    ли
    1.90
    ()));
    
    1.86
    Activations Density 0.003%

    No Known Activations