© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27480
    Prev
    Next
    INDEX
    Explanations

    Poland and Polish language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_width_262k_l0_small_affine
    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
    惫
    0.43
     ఉత్త
    0.43
    ាន
    0.41
     Khartoum
    0.41
     venezolano
    0.41
    湘
    0.40
     Huguen
    0.39
    Mediterr
    0.38
     Mediterr
    0.38
    浙
    0.38
    POSITIVE LOGITS
     Polish
    1.87
    Polish
    1.77
     Poland
    1.71
     поль
    1.71
    Poland
    1.69
     Поль
    1.62
     polish
    1.55
    polish
    1.51
     Pologne
    1.46
     Warsaw
    1.36
    Activations Density 0.050%

    No Known Activations