© 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. 142798
    Prev
    Next
    INDEX
    Explanations

    details and information

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

    if / avoid

    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
    Not in Any Lists

    No Comments

    Negative Logits
    p
    0.60
    ds
    0.58
    k
    0.52
    However
    0.51
     baina
    0.50
    Ds
    0.50
    n
    0.50
    depend
    0.49
    due
    0.48
    ns
    0.47
    POSITIVE LOGITS
    াদনের
    0.47
     Organizer
    0.46
     Sporting
    0.46
     Stunde
    0.46
     választ
    0.45
     särsk
    0.45
    戏剧
    0.44
     fö
    0.43
     özellikle
    0.43
    屿
    0.43
    Activations Density 0.000%

    No Known Activations