© 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. 9769
    Prev
    Next
    INDEX
    Explanations

    calculate assignment condition

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

    The neuron strongly activates on numeric expressions and mathematical notation (numbers, variables, operators, formulas).

    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
    不明白
    -1.86
     utiliser
    -1.77
    茈
    -1.70
    ケモン
    -1.70
    苼
    -1.68
     Eſ
    -1.62
     настоящий
    -1.62
    냑
    -1.60
    詆
    -1.59
    ⽼
    -1.57
    POSITIVE LOGITS
     for
    2.77
     by
    2.44
     with
    2.41
     to
    2.38
     or
    2.27
     from
    2.22
     at
    2.11
     until
    1.95
     in
    1.81
     where
    1.80
    Activations Density 0.035%

    No Known Activations