© 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. 32352
    Prev
    Next
    INDEX
    Explanations

    dates after slashes or numbers

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

    file processing and data handling

    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
    銀座
    0.51
     Grocery
    0.48
     মিসেস
    0.47
     stojí
    0.47
     Nurse
    0.47
    鈐
    0.47
     Store
    0.47
    ﺍ
    0.47
    จีน
    0.46
     Canoe
    0.45
    POSITIVE LOGITS
     इत्या
    0.50
     контроля
    0.49
     தடை
    0.48
    enal
    0.48
    ly
    0.48
     பறி
    0.48
     контроль
    0.47
     exasper
    0.47
    ंगत
    0.47
    पक
    0.46
    Activations Density 0.000%

    No Known Activations