© 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. 218842
    Prev
    Next
    INDEX
    Explanations

    sisters, 姐妹, sisters

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

    following "each"

    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
    나
    0.49
    จัย
    0.46
    icially
    0.46
    τερα
    0.43
    ด
    0.42
    ermanfaat
    0.41
    cepteur
    0.41
    다
    0.41
    Categoria
    0.41
    म्प्ट
    0.41
    POSITIVE LOGITS
     Española
    0.53
     plu
    0.50
    CHN
    0.47
     sisters
    0.47
    姐妹
    0.47
     المس
    0.46
    '
    0.45
     matri
    0.45
    ’-
    0.45
     बहनों
    0.45
    Activations Density 0.000%

    No Known Activations