© 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. 113753
    Prev
    Next
    INDEX
    Explanations

    Bryant, Shelton, Ek

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

    The neuron activates on occurrences of the proper name “Bryant.”

    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
    "
    -3.31
     It
    -3.02
    ться
    -2.83
    -
    -2.78
     et
    -2.61
        
    -2.41
     need
    -2.30
    ко
    -2.30
    та
    -2.20
    Appellants
    -2.16
    POSITIVE LOGITS
    퐸
    2.77
     刺繍
    2.70
     绒
    2.67
    ⢓
    2.61
    쩡
    2.53
    
    2.44
     logros
    2.44
    蠵
    2.39
     rych
    2.36
    ⩤
    2.28
    Activations Density 0.002%

    No Known Activations