© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 38086
    Prev
    Next
    INDEX
    Explanations

    Stanford University

    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
     hards
    -0.85
    大手
    -0.78
    遵循
    -0.78
    葭
    -0.77
     MSP
    -0.76
     exempted
    -0.76
    寐
    -0.74
    ADATA
    -0.73
     liberate
    -0.73
    orgh
    -0.72
    POSITIVE LOGITS
     Stanford
    2.03
    Stanford
    1.78
    stanford
    1.21
     Palo
    1.14
     STANFORD
    0.99
     Hoover
    0.96
     Redwood
    0.88
     Atherton
    0.87
     Menlo
    0.82
     palo
    0.81
    Activations Density 0.023%

    No Known Activations