© 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. 245373
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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
    浼
    0.50
    erView
    0.45
    谓
    0.42
     ترى
    0.41
    的比
    0.41
    رى
    0.39
    诬
    0.39
    鲈
    0.38
    ))/
    0.38
    ới
    0.38
    POSITIVE LOGITS
     aço
    0.54
    ੍ਹਾਂ
    0.54
     punkt
    0.51
     mwaka
    0.51
     difficol
    0.50
    कान
    0.49
     essen
    0.48
    Rek
    0.48
     Punkt
    0.47
    rek
    0.47
    Activations Density 0.000%

    No Known Activations