© 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. 14489
    Prev
    Next
    INDEX
    Explanations

    displaying data, images, or text

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

    The neuron fires strongly on instances of the verb “display” (especially in technical how-to contexts about showing images, data, or 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
    :
    -1.55
     Notwendigkeit
    -1.48
    miques
    -1.39
    ik
    -1.37
     должны
    -1.36
    iao
    -1.35
     Might
    -1.30
     них
    -1.27
    //
    -1.27
     Mereka
    -1.23
    POSITIVE LOGITS
     without
    1.74
     with
    1.69
     even
    1.68
     in
    1.56
     an
    1.40
     just
    1.39
    只是一个
    1.38
     afbeeldingen
    1.36
    gunakan
    1.36
     directly
    1.34
    Activations Density 1.561%

    No Known Activations