© 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. 234769
    Prev
    Next
    INDEX
    Explanations

    payments to physicians

    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
     producten
    0.51
    튜브
    0.51
    탱
    0.50
    어야
    0.48
    베
    0.47
    ют
    0.47
    epro
    0.47
    밸
    0.46
    ሷ
    0.46
     स्टाइल
    0.46
    POSITIVE LOGITS
     E
    0.47
     بحث
    0.47
     all
    0.46
     Mrs
    0.46
     TMA
    0.44
     OECD
    0.43
     Cain
    0.42
     ফে
    0.42
     CA
    0.41
     Reverse
    0.41
    Activations Density 0.002%

    No Known Activations