© 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. 199432
    Prev
    Next
    INDEX
    Explanations

    terms from various languages

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

    punctuation, foreign language, and efficiency

    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
    indak
    0.44
    \
    0.43
    )))
    0.43
     किंवा
    0.41
    lma
    0.41
    (?:
    0.41
    '
    0.41
    ti
    0.41
     Тому
    0.40
    ?')
    0.40
    POSITIVE LOGITS
     puisque
    0.52
     सबके
    0.51
    ोरेशन
    0.51
     hubungan
    0.50
    কল্প
    0.48
     அனைவருக்கும்
    0.48
    ন্টি
    0.47
    ंबकीय
    0.47
    軞
    0.47
     mối
    0.47
    Activations Density 0.002%

    No Known Activations