© 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. 87029
    Prev
    Next
    INDEX
    Explanations

    expect to see

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

    clear statement or description

    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
     panoramic
    0.42
     জটিল
    0.42
    )</
    0.41
     সাফ
    0.39
     fungus
    0.39
     Klass
    0.38
     disputed
    0.38
    щення
    0.38
     ہے۔
    0.38
     ফের
    0.38
    POSITIVE LOGITS
     moje
    0.49
    étera
    0.48
    茜
    0.45
    ří
    0.45
    ět
    0.44
     版
    0.44
    ávy
    0.44
     marki
    0.44
    ugu
    0.44
    pti
    0.44
    Activations Density 0.002%

    No Known Activations