© 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. 23313
    Prev
    Next
    INDEX
    Explanations

    parliamentary questions

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

    asking for information

    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
    軛
    0.44
     prohibition
    0.43
    ensione
    0.42
    지와
    0.42
    allow
    0.42
     prohibitions
    0.42
    EL
    0.40
    %/
    0.40
     sodass
    0.40
     Legislative
    0.40
    POSITIVE LOGITS
    是什么
    0.47
    ົວ
    0.46
     คณิตศาสตร์
    0.43
     Уи
    0.42
     индекс
    0.42
    指数
    0.41
     Chimie
    0.40
    мулятор
    0.40
     другу
    0.39
     localObject
    0.38
    Activations Density 0.001%

    No Known Activations