© 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. 39879
    Prev
    Next
    INDEX
    Explanations

    names starting with Randy

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

    This neuron activates when it encounters the proper name “Randy.”

    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
    舠
    -2.66
    ikusbot
    -2.53
    觏
    -2.52
    </strong>
    -2.41
    𓆜
    -2.39
     she
    -2.27
    萑
    -2.22
     могут
    -2.20
     \
    -2.19
    ୮
    -2.19
    POSITIVE LOGITS
    焢
    2.73
    嗵
    2.69
    
    2.66
    的很
    2.56
    ◆◇
    2.56
    蕷
    2.50
    𖣘
    2.38
    table
    2.38
     didik
    2.36
     transparan
    2.34
    Activations Density 0.002%

    No Known Activations