© 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. 45651
    Prev
    Next
    INDEX
    Explanations

    access to

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

    This neuron detects numerical statistics of “access to” resources—phrases like “access to X” followed by numbers.

    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
    僂
    -1.71
     pulsa
    -1.63
    </i>
    -1.60
     they
    -1.59
    蟊
    -1.53
     asisten
    -1.52
    ();)
    -1.48
     suivez
    -1.48
     planten
    -1.48
    
    -1.48
    POSITIVE LOGITS
    </h4>
    1.85
    s
    1.76
    f
    1.61
     видели
    1.60
     *
    1.59
    v
    1.59
    r
    1.58
    Кроме
    1.56
    However
    1.55
    m
    1.55
    Activations Density 0.013%

    No Known Activations