© 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. 141274
    Prev
    Next
    INDEX
    Explanations

    or

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

    alternative choices

    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
    한
    0.55
    플
    0.49
    پ
    0.48
    쁜
    0.46
    两种
    0.45
    칼
    0.44
    涣
    0.43
    عدة
    0.43
     கி
    0.42
    지
    0.42
    POSITIVE LOGITS
     অথবা
    0.58
    ?...
    0.54
     eller
    0.51
     amer
    0.50
     alebo
    0.50
     Balliye
    0.50
     अथवा
    0.47
    ...?
    0.46
     jsme
    0.46
    หรือ
    0.45
    Activations Density 0.001%

    No Known Activations