© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123859
    Prev
    Next
    INDEX
    Explanations

    animals, percentages, reports

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

    erotic content exclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     zwischen
    0.47
    venture
    0.47
     giữa
    0.46
    zoeken
    0.45
    between
    0.43
    络
    0.43
     between
    0.42
    debug
    0.41
    here
    0.41
     bereit
    0.41
    POSITIVE LOGITS
    ΑΣ
    0.53
    А
    0.49
    ﺍ
    0.49
     hashtags
    0.48
     ორგანო
    0.47
    𝐂
    0.47
     officers
    0.46
    ᄉ
    0.46
     Governorate
    0.45
    ዳ
    0.45
    Activations Density 0.002%

    No Known Activations