© 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. 217227
    Prev
    Next
    INDEX
    Explanations

    in discussions about Washington DC

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

    third party, foreign, others

    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
     r
    0.52
     tyrant
    0.52
     finale
    0.50
     infuri
    0.50
     ’
    0.46
    НЯ
    0.46
     bo
    0.45
     ’’
    0.45
     tantal
    0.44
     dissident
    0.44
    POSITIVE LOGITS
     établ
    0.52
    تين
    0.52
    schap
    0.49
     由于
    0.47
     powod
    0.46
     معرض
    0.46
     يمكن
    0.46
     创建
    0.45
    gegevens
    0.44
    Processes
    0.44
    Activations Density 0.000%

    No Known Activations