© 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. 130366
    Prev
    Next
    INDEX
    Explanations

    with and a

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

    The neuron activates on numeric tokens—especially decimal or high‐value numbers—i.e. measurements and statistical quantities.

    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
    蠱
    -1.70
     it
    -1.60
     некоторых
    -1.49
     thud
    -1.45
    rozco
    -1.41
     stället
    -1.41
     gilded
    -1.40
    bindung
    -1.40
    bhan
    -1.39
     tinged
    -1.38
    POSITIVE LOGITS
     a
    2.77
     an
    1.69
     too
    1.66
    ada
    1.64
    la
    1.64
    new
    1.62
    isation
    1.60
    tahui
    1.59
    an
    1.52
    lan
    1.52
    Activations Density 0.083%

    No Known Activations