© 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. 57010
    Prev
    Next
    INDEX
    Explanations

    return to duty posts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Enfin
    -0.77
    
    -0.75
    INTRODUCTION
    -0.74
     tslint
    -0.73
    Wilson
    -0.72
     wyst
    -0.71
     volete
    -0.70
     Biosciences
    -0.70
    Dalam
    -0.70
     Downtown
    -0.69
    POSITIVE LOGITS
     appointment
    1.01
     appointments
    0.90
    appointment
    0.87
     occup
    0.82
     appointed
    0.82
     pilgrims
    0.82
     hel
    0.77
    appointments
    0.77
     Testa
    0.77
     occupied
    0.76
    Activations Density 0.007%

    No Known Activations