© 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. 246473
    Prev
    Next
    INDEX
    Explanations

    legal and advisory services

    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
    ziemy
    0.48
    槑
    0.48
    岱
    0.47
    薗
    0.47
    ナソニック
    0.47
    رف
    0.46
    枣
    0.46
    速
    0.46
    สัมพันธ์
    0.45
    Interactive
    0.45
    POSITIVE LOGITS
     on
    0.52
     transcend
    0.52
     drawback
    0.52
     ។
    0.49
     tı
    0.48
     frustrate
    0.48
     became
    0.47
     from
    0.47
     حاجات
    0.47
     coming
    0.46
    Activations Density 0.001%

    No Known Activations