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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84908
    Prev
    Next
    INDEX
    Explanations

    stream processing and grouping

    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
    Not in Any Lists

    No Comments

    Negative Logits
      
    -1.65
     more
    -1.63
     are
    -1.61
     $
    -1.53
     
    -1.44
    过敏
    -1.36
     That
    -1.36
    氏が
    -1.30
     Then
    -1.27
    他也
    -1.27
    POSITIVE LOGITS
     ordini
    1.88
    ſſel
    1.73
     militare
    1.66
    ſch
    1.65
    饪
    1.62
    踯
    1.59
    jednoc
    1.58
     aspetti
    1.58
     новую
    1.56
     ultimi
    1.55
    Activations Density 0.004%

    No Known Activations