© 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. 72701
    Prev
    Next
    INDEX
    Explanations

    guaranteed

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

    especially for

    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
    Negative Logits
    0.57
     "
    0.55
     os
    0.47
     wheat
    0.47
     net
    0.46
     trigger
    0.46
     a
    0.46
    ↵
    0.46
     pince
    0.46
    《
    0.45
    POSITIVE LOGITS
     Республи
    0.55
    ராஜ்
    0.54
    Ⲩ
    0.54
     சுற்றுச்சூழ
    0.54
     ຫຼື
    0.53
    이죠
    0.51
     そこ
    0.51
     တော့
    0.50
    poč
    0.50
    த்திலேயே
    0.50
    Activations Density 0.000%

    No Known Activations