© 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. 114326
    Prev
    Next
    INDEX
    Explanations

    device detection improves

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

    try doing something

    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
     Ithaca
    0.47
    els
    0.46
     pleasure
    0.45
     by
    0.44
     thánh
    0.43
    _{+}$
    0.43
     parents
    0.42
     gospel
    0.42
     venne
    0.42
    etown
    0.42
    POSITIVE LOGITS
     проекты
    0.50
     существу
    0.49
     निपटने
    0.47
     поддержку
    0.47
     निर्देशक
    0.46
     масшта
    0.46
    ш
    0.46
    캬
    0.46
    챔
    0.46
     प्रावधान
    0.45
    Activations Density 0.000%

    No Known Activations