© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56685
    Prev
    Next
    INDEX
    Explanations

    Grand Prix, first time, transplant prophylaxis

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

    The neuron fires on the initial, title‐like tokens that start new sections or captions—typically single capitalized letters or words (and associated numbers) at the beginning of a block.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    なのでしょう
    -1.84
    なのかな
    -1.79
    だと思う
    -1.66
    だと思います
    -1.62
     Spéc
    -1.59
     trattano
    -1.59
    様です
    -1.59
     Matériau
    -1.55
     paliwa
    -1.52
     incendie
    -1.49
    POSITIVE LOGITS
    子は
    1.66
    '
    1.63
    子が
    1.58
    ’
    1.51
     پنجم
    1.45
    でございます
    1.39
    はかなり
    1.38
    の
    1.37
     senaste
    1.33
    日から
    1.32
    Activations Density 0.350%

    No Known Activations