© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130592
    Prev
    Next
    INDEX
    Explanations

    charlie

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

    The neuron is a detector for the specific proper name “Charlie.”

    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
    t
    -3.39
    檍
    -3.22
    a
    -3.16
    pecabe
    -2.97
    簠
    -2.77
    ໊
    -2.69
    
    -2.67
    潆
    -2.66
    鴬
    -2.66
    皤
    -2.64
    POSITIVE LOGITS
    <
    3.34
    </i>
    2.97
    The
    2.67
    er
    2.66
    した
    2.50
    ли
    2.50
    Of
    2.50
    剽
    2.47
    Such
    2.44
    ’,
    2.42
    Activations Density 0.002%

    No Known Activations