© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9072
    Prev
    Next
    INDEX
    Explanations

    patterns

    np_acts-logits-general · gemini-2.5-flash-lite

    IAM policies and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EFT
    0.44
     dyst
    0.41
     angels
    0.41
     rollout
    0.40
     saisi
    0.40
     celery
    0.38
    🌱
    0.38
     angel
    0.38
     noms
    0.38
     filos
    0.38
    POSITIVE LOGITS
     urlpatterns
    0.60
     wire
    0.55
    urlpatterns
    0.54
     पैटर्न
    0.52
     patrones
    0.50
     Patterns
    0.48
     Wire
    0.48
    wire
    0.48
     ['(?
    0.46
    patterns
    0.46
    Activations Density 0.007%

    No Known Activations