© 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. 22-GEMMASCOPE-RES-131K
    7. 25284
    Prev
    Next
    INDEX
    Explanations

    people and places

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

    The neuron activates on numeric tokens or headings—i.e. any numbers or number‐based labels in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    -1.16
     skolen
    -1.14
    
    -1.05
    деи
    -1.04
    彡
    -1.04
     Tarif
    -1.02
     peruan
    -1.01
     ferien
    -1.01
     gruppen
    -1.00
    他們
    -0.99
    POSITIVE LOGITS
    now
    0.98
     какой
    0.93
     первым
    0.91
    过来了
    0.91
     Eindruck
    0.90
     -
    0.88
    farlane
    0.88
    時間に
    0.87
    のですか
    0.86
     @
    0.85
    Activations Density 0.070%

    No Known Activations