© 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. 22727
    Prev
    Next
    INDEX
    Explanations

    computer systems and technology

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

    The neuron fires on occurrences of the word “computer” (including in compounds like “computer‐based,” “computer‐aided,” or “computer‐generated”).

    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
    ’
    -2.39
    尤其
    -2.06
    ’，
    -1.87
    UNEP
    -1.79
     comenz
    -1.77
     acqua
    -1.75
     cuid
    -1.74
    她是
    -1.73
     turmeric
    -1.73
     et
    -1.73
    POSITIVE LOGITS
    拍了拍
    2.03
    緜
    1.92
     reasons
    1.88
     what
    1.88
     wykor
    1.87
     enhance
    1.85
     dengan
    1.83
     feiert
    1.82
     utilizzando
    1.80
    轱
    1.79
    Activations Density 0.042%

    No Known Activations