© 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. 22-GEMMASCOPE-RES-131K
    7. 35103
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code

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

    The neuron is detecting numeric tokens (individual digits and numbers) 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
     cintur
    -1.32
     perlas
    -1.24
     nariz
    -1.21
     costuras
    -1.20
     プレミアム
    -1.20
     murales
    -1.17
     gotas
    -1.16
    cameras
    -1.15
    аа
    -1.14
     péro
    -1.13
    POSITIVE LOGITS
     to
    1.21
     डॉ
    1.13
     other
    1.11
     unseres
    1.07
     Некоторые
    1.06
     irgende
    1.05
    ―
    1.05
     alcune
    1.03
     jenen
    0.98
     Should
    0.96
    Activations Density 0.004%

    No Known Activations