© 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. 123672
    Prev
    Next
    INDEX
    Explanations

    proper nouns and foreign words

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

    recognize faces or excuse behavior

    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
    }$\
    0.48
     தோட்டங்கள்
    0.47
     빅
    0.45
     言っ
    0.45
     utterances
    0.44
    ላል
    0.43
    落地
    0.43
     ಇ
    0.43
    អំ
    0.43
     적용
    0.42
    POSITIVE LOGITS
     stör
    0.44
    这部
    0.44
    ަ
    0.44
    ай
    0.42
    According
    0.41
     faibles
    0.41
    ലൈ
    0.41
     Bruno
    0.40
    Xu
    0.40
     Wilbur
    0.40
    Activations Density 0.001%

    No Known Activations