© 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. 97900
    Prev
    Next
    INDEX
    Explanations

    election results, votes, transactions, essential items

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

    Pyramids for Egypt

    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
     @
    0.52
     SaaS
    0.51
    pk
    0.47
     UK
    0.46
     Germany
    0.45
     EUR
    0.45
     SDK
    0.44
    {}
    0.44
    cb
    0.44
    POSITIVE LOGITS
    <unused80>
    0.56
    疗
    0.55
     дерева
    0.54
    ześnie
    0.54
     مرتبہ
    0.53
     gewüns
    0.52
    Fmat
    0.52
    ابقة
    0.51
     ursprüng
    0.50
    اتها
    0.50
    Activations Density 0.001%

    No Known Activations