© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 189577
    Prev
    Next
    INDEX
    Explanations

    warranties arising or of

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

    cum first

    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
     পরিমাণ
    0.46
    とい
    0.45
     തമ്മ
    0.44
    语义
    0.43
     землю
    0.43
     শ্রেণি
    0.42
    颜色
    0.42
     体
    0.41
     कहाँ
    0.41
    体
    0.41
    POSITIVE LOGITS
     it
    0.52
     orifices
    0.48
     cements
    0.47
     ὑ
    0.46
     proprietors
    0.46
     blouses
    0.46
     furnishes
    0.46
     expedit
    0.46
     traject
    0.46
     contemporaries
    0.45
    Activations Density 0.000%

    No Known Activations