© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11273
    Prev
    Next
    INDEX
    Explanations

    government followed by actions

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

    government accountability, spending, and news

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     público
    0.59
     polizia
    0.57
     konkuren
    0.55
    اهرين
    0.55
     policías
    0.54
    ۔
    0.53
     públic
    0.52
    ení
    0.50
     nacional
    0.50
    ၊
    0.50
    POSITIVE LOGITS
    crast
    0.49
    Oj
    0.48
    cip
    0.48
    Wednesday
    0.48
    Simplify
    0.47
    Bran
    0.46
    Sleep
    0.46
    Cloud
    0.46
    Contracts
    0.46
    <0x0D>
    0.45
    Activations Density 0.055%

    No Known Activations