© 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. 102836
    Prev
    Next
    INDEX
    Explanations

    feet, body parts

    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
     Which
    -1.78
    .
    -1.73
    which
    -1.64
     своему
    -1.57
     During
    -1.56
    箋
    -1.55
     TOO
    -1.55
     of
    -1.54
    avaient
    -1.53
    >
    -1.50
    POSITIVE LOGITS
    ዡ
    2.23
    ㍑
    2.20
    銠
    2.03
    
    2.02
    <bos>
    1.99
    
    1.91
     foot
    1.83
    ?”
    1.81
    eſ
    1.81
    matitis
    1.78
    Activations Density 0.025%

    No Known Activations