© 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. 100013
    Prev
    Next
    INDEX
    Explanations

    the + noun

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

    The neuron detects numeric measurement tokens (especially decimal or quantitative 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_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
     renforcé
    -1.79
     tampoco
    -1.68
     comienza
    -1.65
    pulseira
    -1.59
    Secondo
    -1.55
     ทั้ง
    -1.54
    Tutto
    -1.52
    Questa
    -1.51
     rağmen
    -1.51
     "'
    -1.50
    POSITIVE LOGITS
     the
    2.67
    to
    2.20
    with
    1.92
     efforts
    1.91
    as
    1.88
    us
    1.84
    os
    1.83
    ge
    1.79
    which
    1.74
    橚
    1.64
    Activations Density 0.117%

    No Known Activations