© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 6970
    Prev
    Next
    INDEX
    Explanations

    U.S. Patent numbers

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

    The neuron detects numeric tokens containing decimal points or fractional values.

    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
     Memiliki
    -1.31
    Also
    -1.25
    ним
    -1.20
    🤍
    -1.20
    razine
    -1.20
     ६
    -1.16
     být
    -1.15
    愉
    -1.13
     how
    -1.13
     électriques
    -1.09
    POSITIVE LOGITS
     Japón
    1.40
    
    1.28
     ellos
    1.26
     gelungen
    1.25
     invierno
    1.23
     của
    1.21
    dbus
    1.20
     「
    1.20
    }_{\
    1.20
    bedarf
    1.19
    Activations Density 0.120%

    No Known Activations