© 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. 166572
    Prev
    Next
    INDEX
    Explanations

    planning, installing, or finding applications

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

    natural sweeteners

    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
     dih
    0.46
    खास्त
    0.45
     Roskov
    0.44
    合法
    0.44
    েন্টে
    0.44
    手が
    0.43
     dib
    0.43
    拵
    0.43
    его
    0.42
    嫡
    0.42
    POSITIVE LOGITS
    nosi
    0.46
     اتصال
    0.45
     Individuals
    0.45
    álló
    0.44
     Limestone
    0.44
     إلي
    0.44
     ഒന്നും
    0.44
     गुर
    0.44
     Southport
    0.44
     понятие
    0.43
    Activations Density 0.000%

    No Known Activations