© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129042
    Prev
    Next
    INDEX
    Explanations

    anyway

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

    The neuron primarily detects occurrences of the discourse marker “anyway.”

    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
    瞜
    -2.25
    遄
    -2.13
    ↑↑↑</
    -2.11
    ஂ
    -2.02
    栻
    -2.02
     проведение
    -1.99
    らは
    -1.99
    section
    -1.98
    an
    -1.97
     –
    -1.97
    POSITIVE LOGITS
     vierten
    2.52
    薷
    2.36
    菪
    2.34
    癀
    2.31
    臺
    2.30
    쾰
    2.23
     Many
    2.20
     ersche
    2.16
    what
    2.03
    可以说是
    2.03
    Activations Density 0.002%

    No Known Activations