© 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. 235556
    Prev
    Next
    INDEX
    Explanations

    limited bandwidth, speech rights, PhD thesis

    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
     ହ
    0.45
     짜
    0.43
    ร้าย
    0.43
     편리
    0.43
    你了
    0.43
     ไฟล์
    0.42
    ächlich
    0.42
     __
    0.42
     Pleasant
    0.42
    POSITIVE LOGITS
     tono
    0.50
     abuso
    0.46
     limitaciones
    0.45
     مم
    0.43
    তাবাদ
    0.43
    UTIONS
    0.43
    قیه
    0.43
     permanecer
    0.42
     visualise
    0.42
     دوسرے
    0.41
    Activations Density 0.001%

    No Known Activations