© 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. 69515
    Prev
    Next
    INDEX
    Explanations

    ts/TS followed by specific characters or words

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

    The neuron is activated by occurrences of the exact token “ts.”

    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
    遢
    -3.27
    を始め
    -2.86
     sprüche
    -2.80
     ufficio
    -2.78
     suporta
    -2.70
    寕
    -2.67
    を見つけ
    -2.63
    their
    -2.55
    they
    -2.55
    廋
    -2.52
    POSITIVE LOGITS
    de
    2.98
    (
    2.92
            
    2.84
    is
    2.61
    _
    2.50
    ?
    2.47
    -
    2.45
    ’
    2.34
    >
    2.30
    да
    2.28
    Activations Density 0.008%

    No Known Activations