© 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. 6978
    Prev
    Next
    INDEX
    Explanations

    especially

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

    The neuron fires on the three-letter sequence “esp” wherever it appears in a token.

    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
    躝
    -2.78
    齪
    -2.77
     Their
    -2.75
    
    -2.69
    ⫘
    -2.69
     perſon
    -2.64
    
    -2.64
    弍
    -2.59
    ༛
    -2.59
    擼
    -2.59
    POSITIVE LOGITS
    b
    3.77
    k
    3.69
    m
    3.17
    da
    3.08
    O
    2.98
    z
    2.95
    d
    2.91
    w
    2.89
    st
    2.75
    {
    2.75
    Activations Density 0.004%

    No Known Activations