© 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. 86561
    Prev
    Next
    INDEX
    Explanations

    Pauline, Cooke, contamination

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

    The neuron activates for the name "Pauline" and similar variations.

    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
    茕
    -2.55
    鑁
    -2.50
    ,’
    -2.44
    铼
    -2.42
    </h4>
    -2.38
    '")
    -2.36
    犼
    -2.27
    ↵
    -2.25
     horarios
    -2.23
     fie
    -2.22
    POSITIVE LOGITS
    _
    2.73
    –
    2.66
    the
    2.48
    ྅
    2.34
     Both
    2.33
    是有
    2.31
    ༛
    2.31
    ik
    2.31
    ни
    2.23
                    
    2.20
    Activations Density 0.002%

    No Known Activations