© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136078
    Prev
    Next
    INDEX
    Explanations

    following common sequences

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

    scraping and similar phrasing

    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
    Not in Any Lists

    No Comments

    Negative Logits
     WHEN
    0.49
    パーカー
    0.48
    ᴴ
    0.48
     मेक
    0.47
    Σ
    0.47
    ホ
    0.47
    buton
    0.46
     condoms
    0.46
     australia
    0.46
    尭
    0.46
    POSITIVE LOGITS
    یدہ
    0.47
    advertising
    0.43
     Mikhail
    0.43
    featured
    0.42
    krit
    0.42
    recated
    0.42
     listy
    0.41
     Satt
    0.41
    的书
    0.41
    framed
    0.41
    Activations Density 0.001%

    No Known Activations