© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46204
    Prev
    Next
    INDEX
    Explanations

    elected official or speaker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     policym
    0.42
    зыка
    0.42
     consiglio
    0.41
     summons
    0.41
     consultancy
    0.39
     asesor
    0.39
     confiscated
    0.39
     सलाहकार
    0.38
     advise
    0.38
    査
    0.38
    POSITIVE LOGITS
     নির্বাচনের
    0.47
     নির্বাচন
    0.47
    LECTION
    0.46
     தேர்ந்தெடுக்க
    0.46
     escolh
    0.45
    Election
    0.45
     Election
    0.44
     election
    0.43
     nominated
    0.43
     തിരഞ്ഞെടു
    0.42
    Activations Density 0.010%

    No Known Activations