© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 58830
    Prev
    Next
    INDEX
    Explanations

    IT configuration and deployment tools

    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
     avocado
    -0.78
     Ceb
    -0.76
    стюм
    -0.74
    tiste
    -0.73
    Avant
    -0.72
     nyky
    -0.71
     acoustics
    -0.69
     olet
    -0.69
     Avocado
    -0.69
    arela
    -0.68
    POSITIVE LOGITS
     configuration
    0.92
     Ia
    0.90
     Infrastructure
    0.86
     infrastructure
    0.85
     Configuration
    0.84
     configurations
    0.81
    Configuration
    0.80
     code
    0.80
    manif
    0.80
     Vee
    0.79
    Activations Density 0.057%

    No Known Activations