© 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. 74299
    Prev
    Next
    INDEX
    Explanations

    Poland and Polish

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

    Polish language and Poland

    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
    洱
    0.53
    र्यंत
    0.45
     Oahu
    0.45
    儋
    0.45
    𒂊
    0.43
     એલ
    0.43
     Shou
    0.42
     sunscreen
    0.41
    鲛
    0.41
     suficientes
    0.41
    POSITIVE LOGITS
     Polish
    1.59
    Polish
    1.53
     Poland
    1.51
     поль
    1.42
     Поль
    1.41
    Poland
    1.35
     Polonia
    1.28
     Polska
    1.27
     Warsaw
    1.25
     Pologne
    1.23
    Activations Density 0.090%

    No Known Activations