© 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. 72425
    Prev
    Next
    INDEX
    Explanations

    Republican Clean Elections

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

    list, businesses, deliberately, inherited property

    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
    青
    0.49
    学生
    0.49
    Student
    0.45
    U
    0.45
    O
    0.45
    久
    0.45
    এমন
    0.45
    T
    0.44
    To
    0.44
     насе
    0.44
    POSITIVE LOGITS
    ă
    0.48
     també
    0.48
    oucí
    0.48
     వా
    0.48
     ankaŭ
    0.47
     भी
    0.47
    urul
    0.46
    ieto
    0.46
     waa
    0.45
     denominador
    0.45
    Activations Density 0.000%

    No Known Activations