© 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. 229753
    Prev
    Next
    INDEX
    Explanations

    Earnings Recap Expectations

    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
     zariaden
    0.54
     ETH
    0.46
    煙
    0.45
    鹽
    0.44
    轉換
    0.43
    的服务
    0.43
     Theres
    0.42
     acabar
    0.42
    盐
    0.42
     Welcome
    0.41
    POSITIVE LOGITS
    ided
    0.54
    gsub
    0.47
     mysterious
    0.46
    쥔
    0.46
     controversies
    0.46
    ของผู้
    0.44
     calamities
    0.43
    kowo
    0.42
    fairy
    0.42
     घा
    0.42
    Activations Density 0.000%

    No Known Activations