© 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. 32608
    Prev
    Next
    INDEX
    Explanations

    contrasting conditions or outcomes

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

    The neuron fires strongly on very high‐frequency, “function” tokens (common stop words like “the,” “but,” punctuation marks such as commas, and also simple numerals).

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    сам
    -0.94
     raja
    -0.91
    primarily
    -0.91
    Ṫ
    -0.91
     penser
    -0.90
     résoudre
    -0.89
     bättre
    -0.88
    тар
    -0.87
    composed
    -0.86
     kritis
    -0.86
    POSITIVE LOGITS
     if
    2.19
     If
    1.33
    若是
    1.20
    If
    1.13
     якщо
    1.08
     those
    1.04
     but
    1.02
     when
    1.00
     changes
    0.99
     whereas
    0.99
    Activations Density 0.047%

    No Known Activations