© 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. 32480
    Prev
    Next
    INDEX
    Explanations

    consumer product safety issues

    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
     entstehen
    -0.79
     Studien
    -0.78
    InitStruct
    -0.77
    Changed
    -0.77
     literally
    -0.77
    政策
    -0.76
    众
    -0.75
     constantly
    -0.75
     staged
    -0.74
    زین
    -0.74
    POSITIVE LOGITS
    Consumers
    1.07
     consumers
    1.01
     DISTRIBUTION
    1.00
    Distributed
    0.99
     distribution
    0.97
     distributed
    0.96
     Consumers
    0.92
     distribu
    0.92
    distributed
    0.89
     consumidores
    0.88
    Activations Density 0.021%

    No Known Activations