© 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. 18970
    Prev
    Next
    INDEX
    Explanations

    country names after of

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

    countries after "of"

    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
    ერთი
    0.46
    夂
    0.46
    ีย์
    0.45
    Бахар
    0.42
    خ
    0.42
    बाजी
    0.42
    บั
    0.41
    บัน
    0.39
    可以说是
    0.39
    ફેદ
    0.38
    POSITIVE LOGITS
     України
    0.56
    '
    0.54
     Australia
    0.53
     Nigeria
    0.50
     România
    0.50
     India
    0.50
     Kyrgyzstan
    0.50
     Rhodesia
    0.49
     Украины
    0.49
    )”.
    0.49
    Activations Density 0.054%

    No Known Activations