© 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. 172125
    Prev
    Next
    INDEX
    Explanations

    numerical values

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

    negative, incorrect, or harmful concepts

    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
     किरणों
    0.53
    𝚐
    0.49
    ف
    0.46
     संयोजन
    0.46
    𝘨
    0.46
     রশ্ম
    0.46
     بینی
    0.46
     શોધ
    0.46
     ابتدا
    0.45
     перебу
    0.45
    POSITIVE LOGITS
    :“
    0.45
    ശ്ശ
    0.45
     vend
    0.43
     notable
    0.42
     footwear
    0.41
     ladies
    0.41
     bid
    0.41
     “[
    0.41
     несмотря
    0.41
     heave
    0.40
    Activations Density 0.001%

    No Known Activations