© 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. 111979
    Prev
    Next
    INDEX
    Explanations

    documents, browsing, special, thought, products, addict

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

    neurosurgery, queen, stone, kill, reasoning

    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
     υψη
    0.53
     მხ
    0.51
    亠
    0.50
     Học
    0.49
     مب
    0.49
    負責
    0.49
     প্রতিষ্ঠান
    0.48
     腰
    0.47
     quirks
    0.46
    벤
    0.46
    POSITIVE LOGITS
    UE
    0.48
    yam
    0.47
    ln
    0.46
    ogenous
    0.45
    Resources
    0.45
    usted
    0.45
    Ö
    0.44
    ytic
    0.44
    using
    0.44
    ennie
    0.43
    Activations Density 0.000%

    No Known Activations