© 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. 199300
    Prev
    Next
    INDEX
    Explanations

    default Sr licensed community Jewish

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

    ordering and movement

    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
    ויות
    0.46
    Ր
    0.42
     COORDIN
    0.41
    Ꭲ
    0.41
    퍄
    0.41
    훗
    0.41
    Pyrimidine
    0.40
    瓷
    0.40
    Pg
    0.40
    ❖
    0.40
    POSITIVE LOGITS
    datos
    0.50
     वापस
    0.47
    elder
    0.45
     സ്ഥാപ
    0.45
     सूचना
    0.44
     службы
    0.44
     вперед
    0.44
     फाटक
    0.44
     ماحول
    0.44
     நிறுத்த
    0.43
    Activations Density 0.000%

    No Known Activations