© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92029
    Prev
    Next
    INDEX
    Explanations

    to say the least

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

    The neuron strongly activates on common high‐frequency function words (stop words) like “not,” “in,” “small,” “say,” and “least.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    itorious
    -0.71
    cious
    -0.71
    ằng
    -0.71
     Нет
    -0.70
    harusnya
    -0.70
    قديم
    -0.70
     पढ़
    -0.69
    Comentario
    -0.69
     terkenal
    -0.68
    homonymie
    -0.68
    POSITIVE LOGITS
     least
    5.47
    Least
    4.22
    least
    4.22
     Least
    4.06
     LEAST
    3.28
    最小
    2.41
     najm
    2.33
     smallest
    2.22
     mínimo
    1.99
    smallest
    1.96
    Activations Density 0.026%

    No Known Activations