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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39175
    Prev
    Next
    INDEX
    Explanations

    seeing that

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

    The neuron strongly activates on very common short function words (e.g. “that,” “the,” “is,” “a,” “are,” etc.).

    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
    Both
    -1.85
     what
    -1.76
     both
    -1.74
    ременно
    -1.72
     know
    -1.72
    砚
    -1.69
     Both
    -1.65
     would
    -1.63
     want
    -1.61
    However
    -1.59
    POSITIVE LOGITS
     другие
    1.70
     другую
    1.54
     gezogen
    1.50
     realmente
    1.48
     intently
    1.41
    嘴里
    1.38
    のではなく
    1.37
    感じで
    1.35
     erzeugt
    1.34
    ot
    1.33
    Activations Density 0.019%

    No Known Activations