© 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. 3382
    Prev
    Next
    INDEX
    Explanations

    technical content and solutions

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

    The neuron strongly activates on sequences of ASCII‐drawing glyphs (runs of pipes, underscores, slashes/backslashes, etc.), i.e. fragments of monospaced “ASCII art” or diagram characters.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     berät
    -0.78
     apto
    -0.78
     often
    -0.77
     Really
    -0.76
     奈
    -0.75
     really
    -0.75
    يدي
    -0.74
    手紙
    -0.73
    ابس
    -0.73
    父子
    -0.73
    POSITIVE LOGITS
     adidas
    0.82
     spezif
    0.79
     '/';
    0.78
     CSU
    0.77
    ives
    0.77
     gemessen
    0.77
     Forse
    0.75
     aver
    0.75
    ECON
    0.74
    NYSE
    0.73
    Activations Density 0.003%

    No Known Activations