© 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. 75837
    Prev
    Next
    INDEX
    Explanations

    filters and conditions

    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
     olimp
    -1.01
     TikTok
    -0.89
     Customers
    -0.84
     customers
    -0.84
    tvr
    -0.84
    麿
    -0.81
    metik
    -0.79
    artifactId
    -0.77
    싣
    -0.76
    así
    -0.75
    POSITIVE LOGITS
     against
    1.19
     grudge
    1.11
    against
    1.05
     grud
    0.94
    Against
    0.90
     filtros
    0.88
    filter
    0.87
    Filter
    0.87
     FILTER
    0.85
     filter
    0.83
    Activations Density 0.003%

    No Known Activations