© 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. 126500
    Prev
    Next
    INDEX
    Explanations

    foreign words or specific place names

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

    explaining why and how

    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
    к
    0.56
    to
    0.55
    ле
    0.54
    ט
    0.50
    ite
    0.48
    i
    0.47
    г
    0.47
    </h5>
    0.46
    ти
    0.46
    e
    0.46
    POSITIVE LOGITS
     właśnie
    0.51
     مصنوع
    0.48
     উভয়
    0.48
     সমৃদ্ধ
    0.48
     SCE
    0.46
    这里的
    0.46
     উভয়
    0.45
     Hereford
    0.45
    িনী
    0.44
     suivants
    0.43
    Activations Density 0.000%

    No Known Activations