© 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. 176887
    Prev
    Next
    INDEX
    Explanations

    may affect

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

    acronyms and descriptive lists

    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
     umožňuje
    0.59
     spezielle
    0.53
     skriver
    0.53
     behöver
    0.51
    ⼯
    0.51
     utilisent
    0.50
     nutzt
    0.50
     zwięks
    0.50
     omoguć
    0.49
     fonctionne
    0.49
    POSITIVE LOGITS
    лия
    0.45
     stata
    0.45
     unlucky
    0.42
    者
    0.42
    was
    0.41
     imaginations
    0.41
     was
    0.41
    _{*}
    0.41
    ంతా
    0.40
     curls
    0.40
    Activations Density 0.000%

    No Known Activations