© 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. 101003
    Prev
    Next
    INDEX
    Explanations

    Roger followed by surname or initial

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

    The neuron fires on occurrences of the proper name “Roger.”

    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
    ⼥
    -2.86
     you
    -2.48
    ’
    -2.39
    I
    -2.38
    纐
    -2.28
    珦
    -2.22
    ');
    -2.20
    ⢊
    -2.20
     coolest
    -2.17
     they
    -2.14
    POSITIVE LOGITS
    薷
    3.25
    ский
    3.03
    
    2.98
    }
    2.73
    </h3>
    2.63
    </i>
    2.61
    鲼
    2.41
    ;
    2.34
    ことができました
    2.33
    苙
    2.28
    Activations Density 0.002%

    No Known Activations