© 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. 17215
    Prev
    Next
    INDEX
    Explanations

    web links and abbreviations

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

    multi-lingual concepts

    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
    ">
    0.52
    5
    0.51
    1
    0.49
     '
    0.49
     an
    0.48
     JavaScript
    0.46
     Australian
    0.45
    0
    0.45
    0.44
     SQL
    0.44
    POSITIVE LOGITS
    團隊
    0.50
    احنا
    0.46
     briefings
    0.46
     واع
    0.46
    commend
    0.45
    LLCATS
    0.45
     össz
    0.45
     vuttam
    0.45
    kezi
    0.45
     kuiten
    0.45
    Activations Density 0.000%

    No Known Activations