© 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. 83857
    Prev
    Next
    INDEX
    Explanations

    section headers and descriptions

    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
     pertenec
    -1.58
    でしたが
    -1.55
     equipamentos
    -1.45
    
    -1.41
    艄
    -1.39
     этой
    -1.38
    klju
    -1.38
     outono
    -1.37
     funcionan
    -1.37
     таким
    -1.37
    POSITIVE LOGITS
     it
    1.58
    その他の
    1.43
    Other
    1.43
     válvulas
    1.41
    Two
    1.39
    ဴ
    1.38
     vegano
    1.38
     altre
    1.36
     dolorosa
    1.35
    他の
    1.34
    Activations Density 0.092%

    No Known Activations