© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79552
    Prev
    Next
    INDEX
    Explanations

    # followed by various contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    boneca
    -1.60
     aerolí
    -1.45
     Ně
    -1.44
     continuará
    -1.41
    tatuajes
    -1.40
    sukienka
    -1.32
    carteles
    -1.31
     guías
    -1.31
    nefis
    -1.28
     Turquía
    -1.28
    POSITIVE LOGITS
      
    2.09
     는
    1.44
    while
    1.40
       
    1.37
     ,
    1.34
    all
    1.33
    tiously
    1.23
    流石
    1.23
    no
    1.20
    あんまり
    1.20
    Activations Density 0.095%

    No Known Activations