© 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. 79179
    Prev
    Next
    INDEX
    Explanations

    valuation coverage

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

    October, May, bladder, port

    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
     Minneapolis
    0.44
     සම්
    0.44
     fauna
    0.44
     bipartisan
    0.43
    耀
    0.43
     polycarbonate
    0.43
    ্যোগ
    0.42
    otika
    0.42
     ensure
    0.42
     democracy
    0.41
    POSITIVE LOGITS
    CHAPTER
    0.52
    וה
    0.50
     кризи
    0.49
    粔
    0.48
    cours
    0.47
    ()=>{
    0.46
    turb
    0.45
    נון
    0.44
    ственных
    0.44
    ルメ
    0.44
    Activations Density 0.000%

    No Known Activations