© 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. 139443
    Prev
    Next
    INDEX
    Explanations

    presidential election

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

    can give you

    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
    輾
    0.45
    หลากหลาย
    0.42
    週
    0.42
    উপ
    0.40
     wsi
    0.40
    Га
    0.39
    ちょ
    0.39
     بالش
    0.39
    いち
    0.39
    サスカ
    0.38
    POSITIVE LOGITS
    #!
    0.52
     प्रशासन
    0.52
     शिक्षा
    0.50
     adip
    0.47
     कौशल
    0.47
     ઘટના
    0.47
     అధిక
    0.46
    धिकारी
    0.46
    医疗
    0.46
    nehmen
    0.45
    Activations Density 0.001%

    No Known Activations