© 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. 22-GEMMASCOPE-RES-131K
    7. 32799
    Prev
    Next
    INDEX
    Explanations

    classified listings

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

    The neuron detects mentions of classified‐advertising (i.e. “classified” or “classifieds”) 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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     funko
    -0.94
     stärker
    -0.94
     Sitemap
    -0.92
    ä
    -0.91
     spotify
    -0.91
    größern
    -0.89
    xtick
    -0.89
     官网
    -0.88
    ccess
    -0.86
    𝑧
    -0.85
    POSITIVE LOGITS
     listings
    1.56
     listing
    1.30
     ofert
    1.24
     advertisement
    1.20
    ประก
    1.20
     advertisements
    1.19
     selling
    1.17
     Craigslist
    1.13
     originalmente
    1.07
     search
    1.06
    Activations Density 0.043%

    No Known Activations