© 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. 128099
    Prev
    Next
    INDEX
    Explanations

    Botswana, Shawn, rxjs, faucet

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

    The main thing this neuron does is detect capitalized named entities (proper nouns).

    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
    珰
    -2.88
    雠
    -2.86
    湏
    -2.86
    蚡
    -2.72
    鼍
    -2.66
    櫪
    -2.63
    
    -2.55
    <bos>
    -2.55
    ౭
    -2.52
    cursions
    -2.50
    POSITIVE LOGITS
    There
    3.09
    We
    3.08
     There
    2.88
     It
    2.86
    With
    2.78
    It
    2.70
    When
    2.56
     With
    2.45
    They
    2.34
    (
    2.34
    Activations Density 0.023%

    No Known Activations