© 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. 210793
    Prev
    Next
    INDEX
    Explanations

    locations and geographical coverage

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

    fewer people, binary trees, tolerance values

    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
    োধী
    0.49
    .,
    0.47
     ,
    0.45
    ву
    0.44
    countries
    0.44
     অতীত
    0.43
    rael
    0.43
    رافی
    0.43
    などが
    0.42
     polymorphism
    0.41
    POSITIVE LOGITS
    拿下
    0.50
     RICO
    0.48
    貥
    0.46
     RESET
    0.46
    이란
    0.46
     daqui
    0.46
    دق
    0.46
    无限
    0.45
     CAV
    0.45
     Mh
    0.45
    Activations Density 0.002%

    No Known Activations