© 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. 36854
    Prev
    Next
    INDEX
    Explanations

    future plans, facility previously, publication in

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

    search engines

    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
    auf
    0.46
    áže
    0.41
    ř
    0.40
    aufnahme
    0.40
    他
    0.40
    族
    0.40
    iają
    0.39
    এছাড়া
    0.39
    قيق
    0.39
    parseFloat
    0.39
    POSITIVE LOGITS
     ϒ
    0.64
     Ст
    0.55
     Bür
    0.52
     возник
    0.52
     Hs
    0.51
     Κο
    0.50
     वर्गीकृत
    0.50
     règle
    0.50
     Mycobacterium
    0.50
    کات
    0.49
    Activations Density 0.001%

    No Known Activations