© 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. 10-GEMMASCOPE-RES-131K
    7. 103141
    Prev
    Next
    INDEX
    Explanations

    mean or n group

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

    The neuron fires on numerical data tokens—numbers and statistical measures (e.g. means, SEMs, p‐values, decimal values) 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_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
    而出
    -1.48
     religieuses
    -1.44
     chré
    -1.39
     neler
    -1.38
    たまた
    -1.34
     дѣ
    -1.33
     Theologie
    -1.32
    躥
    -1.28
    Distinctions
    -1.27
     addirittura
    -1.27
    POSITIVE LOGITS
     either
    1.68
     combined
    1.49
     must
    1.41
     previous
    1.41
     since
    1.39
     aDecoder
    1.38
    either
    1.36
    .”
    1.33
     }_{
    1.31
     multiple
    1.28
    Activations Density 0.038%

    No Known Activations