© 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. 10-GEMMASCOPE-RES-131K
    7. 98914
    Prev
    Next
    INDEX
    Explanations

    noun followed by punctuation/preposition

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     смогут
    -1.77
    
    -1.56
    抨
    -1.55
    秾
    -1.55
    縢
    -1.51
     такими
    -1.49
    both
    -1.43
     verhindern
    -1.41
    ParallelGroup
    -1.40
    ೣ
    -1.39
    POSITIVE LOGITS
    libatkan
    1.67
    ༘
    1.63
     esmalte
    1.55
     adorno
    1.55
     pintadas
    1.53
    Pgina
    1.48
    kpop
    1.48
     torba
    1.47
    lichten
    1.45
     solares
    1.43
    Activations Density 0.002%

    No Known Activations