© 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. 169271
    Prev
    Next
    INDEX
    Explanations

    fossilised, opposite, level, person's, asylum-seekers

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

    technology, Sentiment, Space, Migration, hosting

    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
    s
    0.63
     and
    0.55
    in
    0.50
     from
    0.48
     لكل
    0.48
     in
    0.47
    ع
    0.47
     Region
    0.46
    :
    0.45
    ق
    0.45
    POSITIVE LOGITS
    ᴛ
    0.61
    駒
    0.52
    𝘣
    0.50
    訓
    0.48
     উপন
    0.48
    𝗷
    0.48
     পারছেন
    0.47
     専用
    0.47
    サーバー
    0.47
    ᇂ
    0.47
    Activations Density 0.001%

    No Known Activations