© 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. 15687
    Prev
    Next
    INDEX
    Explanations

    leather items

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

    The neuron detects mentions of “leather” (i.e. references to leather materials or leather items).

    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
    j
    -3.09
     {
    -3.09
    ‘
    -2.61
    IN
    -2.48
    p
    -2.47
     was
    -2.44
    ad
    -2.38
    ﮏ
    -2.38
    k
    -2.36
    ’;
    -2.33
    POSITIVE LOGITS
     klientów
    2.78
    驁
    2.72
     帅气
    2.72
     Bereichen
    2.66
     сист
    2.59
     vielmehr
    2.56
    訛
    2.48
     speziellen
    2.47
     vollständ
    2.42
    擻
    2.42
    Activations Density 0.007%

    No Known Activations