© 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. 72675
    Prev
    Next
    INDEX
    Explanations

    starting, greater, salary, emails, Cyprus

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

    idioms and phrases

    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
    सिया
    0.46
    чи
    0.43
     Forma
    0.43
    ام
    0.42
    cana
    0.41
    increased
    0.41
    횐
    0.40
     improves
    0.40
     கீ
    0.40
    امام
    0.40
    POSITIVE LOGITS
     مدت
    0.46
     今年
    0.45
     большого
    0.45
    馄
    0.45
    oldCount
    0.45
    èg
    0.44
    ológicas
    0.44
     άλλ
    0.43
     イエロー
    0.43
     ढेर
    0.43
    Activations Density 0.000%

    No Known Activations