© 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. 112524
    Prev
    Next
    INDEX
    Explanations

    Deborah followed by a surname

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

    The neuron strongly activates on occurrences of the proper name “Deborah,” effectively detecting that author byline.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ."
    -2.58
    gebras
    -2.52
    ﮕ
    -2.42
    (
    -2.39
     july
    -2.39
    朦
    -2.39
     护
    -2.38
     '
    -2.38
     как
    -2.34
     儿
    -2.31
    POSITIVE LOGITS
    
    3.09
    <bos>
    2.67
    菹
    2.66
    えっ
    2.59
    椟
    2.53
    さっき
    2.52
    事は
    2.50
    
    2.44
    狆
    2.42
     
    2.36
    Activations Density 0.006%

    No Known Activations