© 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. 8838
    Prev
    Next
    INDEX
    Explanations

    Eli followed by names

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

    The neuron is highly activated by the substring “Eli,” effectively detecting occurrences of the name “Eli” in the text.

    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
    逦
    -2.77
    
    -2.64
     it
    -2.56
     protože
    -2.50
    <bos>
    -2.34
    on
    -2.33
    at
    -2.27
    ar
    -2.27
    but
    -2.23
     подготовка
    -2.22
    POSITIVE LOGITS
    ཋ
    3.67
    ୈ
    3.16
     menyen
    2.83
    ࿙
    2.83
    鲎
    2.80
     himmel
    2.58
    ൎ
    2.56
    鈇
    2.55
    猡
    2.55
     Wikipédia
    2.53
    Activations Density 0.007%

    No Known Activations