© 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. 77963
    Prev
    Next
    INDEX
    Explanations

    rock glaciers, orange aluminum, President James

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

    cruise travel or Protestants

    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
    u
    0.59
     ď
    0.46
    uq
    0.46
    Signal
    0.46
    ILI
    0.45
    alia
    0.44
    ぷ
    0.44
    nexus
    0.43
     Raw
    0.43
     ไอ
    0.43
    POSITIVE LOGITS
     anticipation
    0.58
    رسٹ
    0.57
    ت
    0.54
    عيد
    0.53
     amore
    0.52
     midfielder
    0.50
     adultos
    0.49
     amico
    0.49
    હ
    0.49
     adulto
    0.48
    Activations Density 0.000%

    No Known Activations