© 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. 1528
    Prev
    Next
    INDEX
    Explanations

    abilities, responsibilities, opportunities

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

    handling ambiguity and adjustments

    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
    ﺘ
    0.50
    िया
    0.50
    ٹ
    0.50
    ﻜ
    0.50
     dand
    0.50
    書の
    0.49
    ही
    0.47
    ஸ்தான
    0.46
    ﻛ
    0.46
    ﮔ
    0.46
    POSITIVE LOGITS
     Специа
    0.49
    ł
    0.48
     Collectors
    0.48
     Handling
    0.46
     Repe
    0.46
     एयर
    0.46
     ഇറ
    0.46
     基本
    0.46
    ковка
    0.45
    Popup
    0.44
    Activations Density 0.000%

    No Known Activations