© 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. 226131
    Prev
    Next
    INDEX
    Explanations

    foreign languages and medical terms

    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
    зан
    0.43
     सम्मिल
    0.42
    ёз
    0.42
     непосредственно
    0.41
    и
    0.41
    ҙ
    0.41
    ид
    0.41
    қ
    0.41
     distinctly
    0.40
    ь
    0.40
    POSITIVE LOGITS
     trzech
    0.47
     Kanji
    0.46
     serum
    0.43
    सरत
    0.43
    Serum
    0.42
     કર્યો
    0.42
     zarówno
    0.42
     العد
    0.41
    sera
    0.41
    BSA
    0.41
    Activations Density 0.000%

    No Known Activations