© 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. 108027
    Prev
    Next
    INDEX
    Explanations

    description of consequences

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

    Finnish and specific data

    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
     Chevy
    0.66
     Z
    0.63
     Ebony
    0.63
    '
    0.58
     WI
    0.57
     USAID
    0.57
     брат
    0.56
     Jiu
    0.55
    ’
    0.55
     {
    0.55
    POSITIVE LOGITS
     myös
    1.07
     hyvä
    1.05
     sekä
    1.03
     päiv
    1.02
     käyt
    1.01
     siitä
    1.01
     jälkeen
    1.00
     väl
    1.00
     esimerkiksi
    0.99
     palvel
    0.98
    Activations Density 0.037%

    No Known Activations