© 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. 99913
    Prev
    Next
    INDEX
    Explanations

    accompanied by

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

    The neuron spots instances of “accompanied by” constructions—i.e. the word “accompanied” (often together with “by”) indicating that one thing is accompanied by another.

    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
    '
    -2.33
     collaboratively
    -1.80
    駢
    -1.74
    儲
    -1.72
    ೞ
    -1.69
    はお
    -1.68
    из
    -1.68
    .'”
    -1.65
    le
    -1.63
     而
    -1.63
    POSITIVE LOGITS
    งิน
    2.09
     restes
    1.96
    ⑊
    1.95
    他现在
    1.88
     poches
    1.88
    Dengan
    1.88
     cœurs
    1.83
    儕
    1.82
    他知道
    1.79
    مدل
    1.77
    Activations Density 0.020%

    No Known Activations