© 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. 40659
    Prev
    Next
    INDEX
    Explanations

    tyre, tying typable typhoon

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

    The neuron is keyed to spotting the two‐letter sequence “ty” anywhere in a token.

    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
     –
    -2.69
    愎
    -2.50
    ↵↵
    -2.50
    of
    -2.45
    ations
    -2.44
    in
    -2.38
    ದ
    -2.36
    ↵
    -2.34
    us
    -2.33
     ploy
    -2.33
    POSITIVE LOGITS
    ty
    2.80
    橚
    2.70
    replyreport
    2.70
    umpulan
    2.55
    /
    2.48
    ⾦
    2.47
    箇
    2.39
    enablog
    2.34
    ዬ
    2.25
    udadera
    2.20
    Activations Density 0.020%

    No Known Activations