© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2465
    Prev
    Next
    INDEX
    Explanations

    Polish places and people

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

    Poland and Warsaw

    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_53_width_65k_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
     Essentially
    0.47
     ఇంత
    0.46
    ຖືກ
    0.45
     nefarious
    0.43
     essentially
    0.43
     શ્રી
    0.43
    遢
    0.43
     ડિઝ
    0.43
     techs
    0.43
     relativo
    0.42
    POSITIVE LOGITS
     Polish
    1.51
     Michał
    1.44
     Wrocław
    1.44
    Polish
    1.41
     Kraków
    1.37
     Rafał
    1.33
     Poland
    1.32
     Polska
    1.31
     Ł
    1.30
     Andrzej
    1.29
    Activations Density 0.135%

    No Known Activations