© 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. 10-GEMMASCOPE-RES-131K
    7. 74478
    Prev
    Next
    INDEX
    Explanations

    creative works

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

    The neuron consistently lights up on plural nouns naming content or offerings (e.g. articles, posts, products, images, designs, works, services).

    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
     of
    -2.23
     where
    -2.16
     in
    -2.14
     it
    -1.59
     upaya
    -1.51
     like
    -1.50
    żdż
    -1.38
     what
    -1.33
     /
    -1.33
     all
    -1.33
    POSITIVE LOGITS
     Terbaru
    1.66
    Regarding
    1.60
     MUCH
    1.55
     BOOM
    1.54
     THOSE
    1.47
     THESE
    1.47
     dévou
    1.46
     DAMN
    1.45
     distinguer
    1.45
    panasonic
    1.45
    Activations Density 0.078%

    No Known Activations