© 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. 6624
    Prev
    Next
    INDEX
    Explanations

    listing pairs

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

    y/and/or

    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
     καὶ
    0.38
    ၊
    0.37
     এবং
    0.35
     и
    0.34
     ချ
    0.34
     edhe
    0.34
     kés
    0.34
     場
    0.33
     শ্রেণ
    0.33
     และ
    0.32
    POSITIVE LOGITS
    /
    0.48
     whatnot
    0.46
     sebagainya
    0.42
     में
    0.37
     the
    0.34
     tiež
    0.33
     some
    0.32
    lor
    0.32
    REW
    0.32
     to
    0.32
    Activations Density 0.414%

    No Known Activations