© 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. 27266
    Prev
    Next
    INDEX
    Explanations

    African countries and regions

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

    africa and african

    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
     αξ
    0.55
     पर्यटक
    0.55
    膘
    0.52
     అన్ని
    0.51
    icts
    0.51
     관광
    0.50
    ervices
    0.50
    აპ
    0.49
    annya
    0.49
     앞
    0.49
    POSITIVE LOGITS
     African
    0.80
     Africa
    0.75
    African
    0.75
     afric
    0.74
     nigeria
    0.70
     africa
    0.68
    Africa
    0.68
     niger
    0.68
    非洲
    0.68
     Nigerian
    0.66
    Activations Density 0.014%

    No Known Activations