© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13599
    Prev
    Next
    INDEX
    Explanations

    group and numeral/letter identifiers

    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
     for
    -2.25
     
    -2.23
     It
    -1.78
     таких
    -1.49
     was
    -1.45
     is
    -1.44
    もありました
    -1.43
     такого
    -1.42
      
    -1.40
    If
    -1.39
    POSITIVE LOGITS
     miliki
    2.14
     our
    1.88
    珦
    1.81
     each
    1.77
    juga
    1.52
     politiet
    1.51
     the
    1.50
     kirke
    1.48
     Harus
    1.47
    
    1.46
    Activations Density 0.062%

    No Known Activations