© 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. 50894
    Prev
    Next
    INDEX
    Explanations

    Registered persons

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

    sharing opportunities

    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
     سلامه
    0.56
     غز
    0.52
     کی
    0.51
     استعمال
    0.50
    ・
    0.48
     행사
    0.48
    quela
    0.47
    insurance
    0.47
     اینڈ
    0.46
    ز
    0.45
    POSITIVE LOGITS
    ಾಗಿ
    0.44
     Factories
    0.41
     actors
    0.40
    speople
    0.39
     வா
    0.38
    Attrs
    0.38
     Opportunities
    0.38
     Pool
    0.38
     વૈ
    0.38
    掊
    0.38
    Activations Density 0.000%

    No Known Activations