© 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. 128231
    Prev
    Next
    INDEX
    Explanations

    words like shipper, learnt, storm, wreck

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

    specific types or lists

    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
     insights
    0.54
     exemplified
    0.51
    シルバー
    0.50
     зв
    0.49
    گ
    0.48
     सूखा
    0.46
    م
    0.45
    ライト
    0.43
     кварта
    0.43
    𐰢
    0.43
    POSITIVE LOGITS
    τους
    0.48
     sementara
    0.47
     veril
    0.46
    取得
    0.45
    ្វី
    0.44
    kelijke
    0.43
     meanwhile
    0.43
     mesmos
    0.43
    喏
    0.43
     Ghan
    0.42
    Activations Density 0.000%

    No Known Activations