© 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. 73237
    Prev
    Next
    INDEX
    Explanations

    ust and UST

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

    The neuron fires on the three-letter sequence “ust” wherever it appears within a word.

    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
     selben
    -3.16
    selben
    -2.98
     We
    -2.86
     Because
    -2.77
    镠
    -2.72
     Потому
    -2.69
     Häufig
    -2.64
     unangemessene
    -2.58
     häufigsten
    -2.58
    
    -2.56
    POSITIVE LOGITS
    s
    5.91
    a
    3.56
    ust
    3.13
    ’
    2.81
    d
    2.70
    水が
    2.50
    t
    2.47
    ثيق
    2.44
    vably
    2.44
    ा
    2.34
    Activations Density 0.009%

    No Known Activations