© 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. 15934
    Prev
    Next
    INDEX
    Explanations

    USA or American in multiple languages

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

    US market economics

    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
     headache
    0.47
     Franck
    0.47
     SimSun
    0.44
     Hoping
    0.43
     Piazza
    0.43
    OfString
    0.43
     Szcz
    0.43
    壁
    0.41
     Brett
    0.41
    basicConfig
    0.41
    POSITIVE LOGITS
    ಕೊ
    0.50
     américain
    0.48
    美國
    0.47
     মার্কিন
    0.46
     американский
    0.46
     Amerikaanse
    0.46
     любят
    0.45
     egyéb
    0.45
     иных
    0.44
     அமெரிக்க
    0.43
    Activations Density 0.000%

    No Known Activations