© 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. 85199
    Prev
    Next
    INDEX
    Explanations

    on behalf of purpose

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

    talk about exploration

    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
    ா
    0.52
    า
    0.46
    jár
    0.46
    ariski
    0.46
     burdensome
    0.45
    ances
    0.45
     দলটি
    0.44
    𝑎
    0.44
    會在
    0.43
     যাবার
    0.43
    POSITIVE LOGITS
     milyon
    0.51
     смерти
    0.49
     svojim
    0.47
     namam
    0.47
     Trời
    0.47
     meninggal
    0.46
     św
    0.46
     svoje
    0.45
    čiti
    0.45
     śmierci
    0.45
    Activations Density 0.001%

    No Known Activations