© 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. 6772
    Prev
    Next
    INDEX
    Explanations

    following definitive articles and words

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

    comprehensive introduction, sequence, innovation

    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
    шены
    0.46
    ة
    0.46
    ब
    0.46
     ब
    0.45
     কুর
    0.44
    لات
    0.44
     wn
    0.43
     벌
    0.43
     This
    0.43
    ণী
    0.43
    POSITIVE LOGITS
     Gottlieb
    0.52
     PSE
    0.49
    会不会
    0.48
    க்கிர
    0.46
    dataTable
    0.46
    浸
    0.46
    ຂໍ
    0.45
    division
    0.45
     FRANCE
    0.45
     verr
    0.45
    Activations Density 0.000%

    No Known Activations