© 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. 34-GEMMASCOPE-RES-131K
    7. 64884
    Prev
    Next
    INDEX
    Explanations

    changes in status

    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
     actuels
    -1.14
     esempi
    -1.08
    Aktu
    -1.05
    differences
    -0.98
    Differences
    -0.98
     élevée
    -0.96
     ISSUES
    -0.96
     actuellement
    -0.95
     antigüedad
    -0.94
     菇
    -0.94
    POSITIVE LOGITS
     composition
    1.63
     circumstances
    1.55
     configuration
    1.54
     patterns
    1.53
     structure
    1.48
     priorities
    1.46
     attitudes
    1.45
     fortunes
    1.40
     attitude
    1.39
     status
    1.36
    Activations Density 0.128%

    No Known Activations