© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9319
    Prev
    Next
    INDEX
    Explanations

    emphasizing key information

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    по
    0.29
    ται
    0.27
     Additionally
    0.27
    ちなみに
    0.26
    ளுக்காக
    0.26
    越し
    0.26
    াপাশি
    0.26
    विण्यासाठी
    0.26
    ጇ
    0.26
     Например
    0.25
    POSITIVE LOGITS
     they
    0.40
     nunca
    0.38
     never
    0.37
    i
    0.37
     there
    0.35
     we
    0.34
    e
    0.34
    这是一
    0.32
    ،
    0.32
    ，
    0.31
    Activations Density 0.123%

    No Known Activations