© 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. 71819
    Prev
    Next
    INDEX
    Explanations

    names ending in stein

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

    The neuron activates on capitalized personal names (surnames) in text.

    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
    e
    -3.45
    
    -2.86
    的最大
    -2.45
    塒
    -2.39
    蕷
    -2.34
    儅
    -2.33
    <i>
    -2.31
    鱟
    -2.30
    u
    -2.28
    渽
    -2.28
    POSITIVE LOGITS
    </em>
    3.06
    \
    2.83
    ጢ
    2.59
    狨
    2.58
     It
    2.47
    もお
    2.28
     And
    2.22
     Occasionally
    2.20
    ),
    2.17
    ."
    2.17
    Activations Density 0.002%

    No Known Activations