© 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. 99090
    Prev
    Next
    INDEX
    Explanations

    database transaction isolation levels

    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
     boat
    -0.82
    arta
    -0.81
     Cham
    -0.78
     already
    -0.75
     Boiler
    -0.73
    坎
    -0.73
     mic
    -0.72
    纵
    -0.70
    πό
    -0.69
    garder
    -0.68
    POSITIVE LOGITS
     consistency
    2.02
     Consistency
    1.91
    consistency
    1.78
    Consistency
    1.74
     consistent
    1.20
    Consistent
    1.20
    eventually
    1.16
    consistent
    1.15
     Consistent
    1.15
    Eventually
    1.11
    Activations Density 0.055%

    No Known Activations