© 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. 10262
    Prev
    Next
    INDEX
    Explanations

    tree bark

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

    references to tree bark or bark-related materials.

    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
    
    -1.81
    lossians
    -1.77
    Ruju
    -1.77
    偸
    -1.77
    塍
    -1.75
    quelize
    -1.72
     uruguay
    -1.70
     extérieur
    -1.70
    說話
    -1.69
     MINISTER
    -1.67
    POSITIVE LOGITS
    ↵
    2.42
     of
    2.31
    、『
    1.86
    P
    1.80
    thschild
    1.78
    S
    1.78
     worauf
    1.77
     they
    1.77
     obwohl
    1.75
     alleged
    1.74
    Activations Density 0.010%

    No Known Activations