© 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. 22-GEMMASCOPE-RES-131K
    7. 36487
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and logic

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

    This neuron responds to numeric tokens (numbers and numeric 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_22/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
    лено
    -0.90
     what
    -0.85
     formales
    -0.83
     Ні
    -0.79
     közé
    -0.78
     Tokyo
    -0.78
     focusing
    -0.75
    nitrogen
    -0.75
     with
    -0.75
     Aud
    -0.75
    POSITIVE LOGITS
     모든
    0.94
     impromptu
    0.91
    뒤
    0.91
     déterminer
    0.90
    잘
    0.89
     onerous
    0.87
    졍
    0.85
     kleinere
    0.84
    不需要
    0.84
     tremendous
    0.83
    Activations Density 0.024%

    No Known Activations