© 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. 86606
    Prev
    Next
    INDEX
    Explanations

    TX in Texas

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

    The neuron strongly activates on the token “TX” (e.g. the two-letter abbreviation in product codes, state postal codes, or protocol/message names).

    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
    0
    -3.22
    </strong>
    -3.22
     ")[
    -3.02
    </sub>
    -2.73
     “
    -2.67
    that
    -2.64
    '
    -2.61
    </h3>
    -2.53
     feiner
    -2.48
     усі
    -2.45
    POSITIVE LOGITS
    穑
    2.98
    镡
    2.75
    wijl
    2.72
    蔸
    2.59
    ඬ
    2.56
    솝
    2.55
    τής
    2.48
    ef
    2.48
    텃
    2.44
    皲
    2.42
    Activations Density 0.004%

    No Known Activations