© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39424
    Prev
    Next
    INDEX
    Explanations

    guy's name

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

    The neuron fires on the two-token pattern of a capitalized first name “Guy” immediately followed by a capital “F” (i.e. the start of “Guy F…”).

    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
    鑁
    -2.70
     Reſ
    -2.59
    zelfde
    -2.59
    附近的
    -2.52
    踅
    -2.47
     französische
    -2.36
    跸
    -2.36
    注意事
    -2.31
    umumkan
    -2.30
    
    -2.30
    POSITIVE LOGITS
            
    2.86
    :
    2.66
    ↵↵
    2.52
    }
    2.48
    <i>
    2.42
    </strong>
    2.38
    The
    2.38
    する
    2.34
     ‘
    2.33
    These
    2.33
    Activations Density 0.004%

    No Known Activations