© 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. 74825
    Prev
    Next
    INDEX
    Explanations

    describing items or people

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

    technical changes and user interface

    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
    ҙ
    0.48
    濟
    0.46
     exoskeleton
    0.46
    ү
    0.45
    चा
    0.45
    disable
    0.44
    ји
    0.44
    ក្រ
    0.43
    というと
    0.43
    жение
    0.43
    POSITIVE LOGITS
     패턴
    0.50
     Prü
    0.47
     เปลี่ยน
    0.46
     Demon
    0.44
     Thay
    0.43
     반응
    0.43
     让
    0.43
     Replication
    0.42
     এলাকায়
    0.42
     업데이트
    0.42
    Activations Density 0.000%

    No Known Activations