© 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. 81362
    Prev
    Next
    INDEX
    Explanations

    access, results, film, monitoring, Gospel, performance

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

    scraping, border, port, climbing, hash

    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
     பணம்
    0.48
    umboldt
    0.47
    ھا
    0.47
    repetitions
    0.46
    简洁
    0.46
    该公司
    0.46
    粖
    0.46
     Plugins
    0.45
     फिल्में
    0.45
     ارائه
    0.45
    POSITIVE LOGITS
     viy
    0.51
    *
    0.48
     pat
    0.45
     settle
    0.44
     scatter
    0.43
    面の
    0.42
    od
    0.41
    ár
    0.41
     van
    0.41
    Bag
    0.40
    Activations Density 0.001%

    No Known Activations