© 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. 111219
    Prev
    Next
    INDEX
    Explanations

    probability distributions

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

    The neuron strongly activates on occurrences of the term “distribution,” in particular when referring to probability or statistical distributions.

    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
     Inſ
    -2.44
    ++){
    -2.22
    埽
    -2.11
    actéristi
    -2.08
    nicity
    -2.06
    ſſen
    -2.05
    ᵴ
    -2.03
     Reſ
    -1.96
     Dinas
    -1.95
    strukturen
    -1.94
    POSITIVE LOGITS
     any
    2.03
     meticulously
    1.83
    ſelves
    1.77
     more
    1.72
     nearing
    1.71
    -
    1.70
     cleverly
    1.70
     colorida
    1.69
     motivadoras
    1.69
     exquisite
    1.67
    Activations Density 0.023%

    No Known Activations