© 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. 10-GEMMASCOPE-RES-131K
    7. 68739
    Prev
    Next
    INDEX
    Explanations

    words starting with 'bal' or 'pell'

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

    This neuron fires on unusual proper names—especially non-English or transliterated terms (e.g. Latin species names, foreign place or instrument names).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    瞅
    -1.63
    んじゃ
    -1.37
    그러나
    -1.35
    Nyt
    -1.31
    recently
    -1.31
    こういった
    -1.30
    웹
    -1.29
    Юлия
    -1.28
    じゃあ
    -1.27
    なるほど
    -1.26
    POSITIVE LOGITS
    berapa
    1.59
     only
    1.56
    四年
    1.53
    ׇ
    1.48
     alvor
    1.46
    ！"
    1.38
    "));
    1.36
    </td>
    1.36
     冬
    1.36
    七年
    1.32
    Activations Density 0.097%

    No Known Activations