© 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. 113949
    Prev
    Next
    INDEX
    Explanations

    bold + descriptive word

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

    The neuron strongly activates on occurrences of the word “bold.”

    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
     They
    -2.56
    ’
    -2.52
     ‘’
    -2.52
     [...]
    -2.44
    vantaged
    -2.38
    霎
    -2.38
    sonaro
    -2.34
     Their
    -2.34
    <strong>
    -2.28
     \'
    -2.20
    POSITIVE LOGITS
    7
    3.06
    6
    3.05
    1
    2.91
    4
    2.83
    5
    2.77
    8
    2.64
    經常
    2.55
    䊏
    2.38
    ing
    2.36
    经常
    2.36
    Activations Density 0.002%

    No Known Activations