© 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. 236871
    Prev
    Next
    INDEX
    Explanations

    to be

    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
    UIntValue
    0.59
     adhipp
    0.55
     repas
    0.54
     IUnary
    0.51
     соответ
    0.50
     도형
    0.49
     значения
    0.49
     коли
    0.49
     🌱
    0.48
     pavattati
    0.47
    POSITIVE LOGITS
    to
    0.73
    on
    0.66
    pool
    0.61
    kho
    0.57
    kum
    0.56
    water
    0.55
    mid
    0.55
    ik
    0.54
    cities
    0.53
    room
    0.53
    Activations Density 0.000%

    No Known Activations