© 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. 68626
    Prev
    Next
    INDEX
    Explanations

    article snippets

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

    The neuron fires on editorial interface labels and metadata markers (e.g. “CAPTIONS:”, “PHOTO:”, “MORE”, “Receive”) rather than on normal article text.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     our
    -1.74
     strangely
    -1.57
     blatantly
    -1.51
     what
    -1.50
     surprisingly
    -1.50
     diligently
    -1.48
     your
    -1.47
     or
    -1.45
     cleverly
    -1.45
     for
    -1.44
    POSITIVE LOGITS
     Dinas
    1.91
    戋
    1.87
     .........
    1.61
     paus
    1.56
     departe
    1.56
     musul
    1.55
     ultime
    1.55
     garan
    1.54
     utop
    1.54
     dì
    1.53
    Activations Density 0.021%

    No Known Activations