© 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. 38467
    Prev
    Next
    INDEX
    Explanations

    objects like sheets, bags, or cards

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

    The neuron fires on nouns naming specific physical products or device components (e.g., Pen, bands, Suit, patch, sheet) in technical or commercial contexts.

    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
     ceket
    -1.46
     großen
    -1.43
     elbise
    -1.38
     ayakkab
    -1.34
     gömlek
    -1.30
     įva
    -1.30
     with
    -1.29
     Eindruck
    -1.26
     Since
    -1.25
     descansar
    -1.24
    POSITIVE LOGITS
    inputStream
    1.65
     noen
    1.38
    髣
    1.34
    1.32
     participe
    1.31
    fgaben
    1.31
    argc
    1.30
     与
    1.30
    
    1.28
    涠
    1.27
    Activations Density 0.113%
    No Known Activations