© 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. 53334
    Prev
    Next
    INDEX
    Explanations

    caucus elections

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

    magnitude of potential drop

    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
     인기
    0.50
     沖縄
    0.49
     抗
    0.49
     κοινων
    0.48
     각
    0.48
     インド
    0.48
     شب
    0.47
     다니
    0.47
     యువ
    0.47
     оказыва
    0.47
    POSITIVE LOGITS
    प्रिंट
    0.51
    фор
    0.49
    пе
    0.49
    স্ত্রী
    0.49
    вла
    0.48
    ние
    0.48
    п
    0.47
     doit
    0.46
     change
    0.46
    は
    0.46
    Activations Density 0.000%

    No Known Activations