© 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. 208099
    Prev
    Next
    INDEX
    Explanations

    company, search, reported, times, my, versions, come

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

    'alright class' as introduction

    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
    1
    0.44
    2
    0.43
    3
    0.43
    殴
    0.43
     rackets
    0.43
     evangel
    0.42
    kyo
    0.42
     MG
    0.41
    GER
    0.40
    ించాలని
    0.40
    POSITIVE LOGITS
    quefois
    0.56
    getRoot
    0.50
    chodzi
    0.49
     କରି
    0.48
    amount
    0.48
    পাত
    0.48
     最後
    0.48
    not
    0.47
     那
    0.47
     Labrenzia
    0.47
    Activations Density 0.000%

    No Known Activations