© 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. 228417
    Prev
    Next
    INDEX
    Explanations

    strong delusion

    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
     университе
    0.49
     klient
    0.47
     እስከ
    0.47
     universitet
    0.46
    два
    0.46
    koliko
    0.46
    Q
    0.45
    قد
    0.45
     खेलों
    0.45
     direktor
    0.45
    POSITIVE LOGITS
     type
    0.50
    ง่าย
    0.41
    ্রি
    0.41
     বিচ্ছিন্ন
    0.40
    metric
    0.40
    TestSource
    0.40
    ritable
    0.39
    readystatechange
    0.39
     tumour
    0.39
     bonheur
    0.39
    Activations Density 0.000%

    No Known Activations