© 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. 226877
    Prev
    Next
    INDEX
    Explanations

    olive grove

    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
     iā
    0.55
    ክምና
    0.54
    IRCONIUM
    0.53
    ጒ
    0.50
     lézards
    0.49
    橢
    0.48
     professores
    0.48
    ეგისტრ
    0.48
     процен
    0.47
    群体
    0.47
    POSITIVE LOGITS
    0.52
     Mas
    0.51
     Se
    0.49
     M
    0.48
     J
    0.48
     Re
    0.47
    or
    0.47
    ors
    0.46
     است
    0.45
     Gal
    0.45
    Activations Density 0.000%

    No Known Activations