© 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. 41826
    Prev
    Next
    INDEX
    Explanations

    words starting with Th

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

    The neuron consistently activates on tokens that begin with the letters “Th,” marking words or fragments that start with “Th.”

    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
    ſelf
    -3.73
    曁
    -3.27
    to
    -3.06
     باسلام
    -2.97
    </u>
    -2.69
    」
    -2.69
    ႏ
    -2.63
    儈
    -2.61
    핥
    -2.59
    」（
    -2.56
    POSITIVE LOGITS
    o
    3.00
    ’
    2.48
    \
    2.47
    {
    2.39
    T
    2.36
    <
    2.31
    en
    2.28
    ;
    2.27
    埝
    2.22
     notre
    2.20
    Activations Density 0.004%

    No Known Activations