© 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. 104732
    Prev
    Next
    INDEX
    Explanations

    words starting with St

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

    The neuron responds to the two‐letter subword “St,” i.e. tokens beginning with the characters “St.”

    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
    呖
    -3.33
    螓
    -2.97
    ſelves
    -2.80
    with
    -2.53
    镔
    -2.45
     Perfon
    -2.44
     sostener
    -2.38
     rústica
    -2.34
     beneficiario
    -2.34
    no
    -2.34
    POSITIVE LOGITS
     '
    3.28
    
    2.88
    鬭
    2.81
    *
    2.78
     zarówno
    2.58
    ');
    2.56
     Of
    2.53
     proverbial
    2.53
     is
    2.47
    妧
    2.47
    Activations Density 0.029%

    No Known Activations