© 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. 45545
    Prev
    Next
    INDEX
    Explanations

    items and their industries

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

    The neuron fires strongly on mentions of concrete consumer products or merchandise categories (e.g. gear, watches, socks, pens, shoes, carpets).

    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
    </sup>
    -1.53
    <h3>
    -1.51
     you
    -1.49
    你不
    -1.48
    ```
    -1.41
     if
    -1.38
     huellas
    -1.38
    其
    -1.36
    他の
    -1.35
     peores
    -1.34
    POSITIVE LOGITS
    &
    1.70
     of
    1.55
    künfte
    1.48
    壜
    1.48
    €.
    1.39
    +',
    1.38
     pneu
    1.37
    arture
    1.37
    °;
    1.37
    ólogo
    1.36
    Activations Density 0.192%

    No Known Activations