© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42453
    Prev
    Next
    INDEX
    Explanations

    Yann, Yok after names

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

    This neuron responds to uncommon two-letter (and similar) consonant clusters or gibberish letter sequences.

    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
    th
    -3.03
    0
    -3.00
    ">
    -3.00
    </b>
    -2.77
    ");
    -2.77
    ()
    -2.72
    at
    -2.58
    }{
    -2.55
     were
    -2.42
    in
    -2.36
    POSITIVE LOGITS
    
    3.52
    lossians
    2.88
     Japón
    2.80
    
    2.64
    へ向
    2.63
     Alemania
    2.59
    逦
    2.50
    狲
    2.48
    桫
    2.45
    蛲
    2.44
    Activations Density 0.461%

    No Known Activations