© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20158
    Prev
    Next
    INDEX
    Explanations

    keloid

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

    The neuron detects the name prefix "Kel" in various words including keloid, Kellogg, Kelvingrove, and names starting with Kel.

    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
    棪
    -2.72
    </i>
    -2.53
    anjutan
    -2.52
     放題
    -2.41
    ”،
    -2.39
     conceptions
    -2.36
    蠵
    -2.33
     stances
    -2.30
    儇
    -2.30
    </u>
    -2.28
    POSITIVE LOGITS
    >
    2.83
     }
    2.69
    </h2>
    2.50
     &
    2.33
     TMPro
    2.28
     \
    2.27
    ;
    2.27
    
    2.19
    ()
    2.19
     `
    2.17
    Activations Density 0.002%

    No Known Activations