© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44211
    Prev
    Next
    INDEX
    Explanations

    locations and institutions

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

    The neuron activates on numeric tokens—especially decimal numbers—marking occurrences of measurements or other numerical data.

    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
     our
    -1.78
    或
    -1.18
     its
    -1.17
    ",
    -1.16
     important
    -1.14
    about
    -1.14
    includes
    -1.13
    anasia
    -1.13
     naszych
    -1.13
     it
    -1.09
    POSITIVE LOGITS
    february
    1.16
     ？
    1.09
     for
    1.08
     Pentru
    1.06
    january
    1.05
    棪
    1.04
    dijual
    1.04
     两
    1.03
     什么
    1.03
    ighed
    1.02
    Activations Density 0.101%

    No Known Activations