© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86052
    Prev
    Next
    INDEX
    Explanations

    TA abbreviation or part of name

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

    The neuron activates specifically on the two-letter uppercase token “TA.”

    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
    ра
    -2.47
    䉴
    -2.45
    是
    -2.34
    大量的
    -2.30
     моя
    -2.20
    ÇÕES
    -2.19
    赑
    -2.13
    чной
    -2.11
    炖
    -2.11
     ehemalige
    -2.08
    POSITIVE LOGITS
    --
    3.11
    "...
    2.66
    TA
    2.48
    "-
    2.45
    -"
    2.27
    猡
    2.25
     "
    2.16
    سبة
    2.11
    "\
    2.09
    your
    2.09
    Activations Density 0.006%

    No Known Activations