© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 906
    Prev
    Next
    INDEX
    Explanations

    self- words and itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    新
    1.18
    ቛ
    1.18
    Ко
    1.14
    Κα
    1.09
    Се
    1.08
    Мы
    1.08
    䄱
    1.08
    他们
    1.05
    こと
    1.05
    Из
    1.05
    POSITIVE LOGITS
    ↵
    1.28
     (
    1.12
      
    1.10
    ä
    1.04
    ;
    0.95
     self
    0.93
    self
    0.92
     Self
    0.91
    o
    0.88
     the
    0.87
    Activations Density 0.377%

    No Known Activations