© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2263
    Prev
    Next
    INDEX
    Explanations

    nations and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    x
    0.60
    dır
    0.58
    на
    0.57
     Cantonese
    0.56
    e
    0.53
    where
    0.53
    ванням
    0.53
    м
    0.52
    ʀ
    0.52
     бота
    0.52
    POSITIVE LOGITS
     nations
    0.67
     republics
    0.62
     countries
    0.56
     troops
    0.55
     democracies
    0.54
     politics
    0.54
     governments
    0.53
     government
    0.53
     politici
    0.53
     supremacist
    0.52
    Activations Density 0.322%

    No Known Activations