© 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. 604
    Prev
    Next
    INDEX
    Explanations

    automotive industry components

    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
     Cerebral
    -0.76
     żyw
    -0.73
    痘
    -0.66
    ServiceModel
    -0.66
     Garry
    -0.65
     Concrete
    -0.65
    casio
    -0.65
     Brooklyn
    -0.65
     concreto
    -0.64
     Leinwand
    -0.64
    POSITIVE LOGITS
     supplier
    1.65
     suppliers
    1.59
     component
    1.45
     components
    1.44
     automotive
    1.39
    supplier
    1.36
    Tier
    1.35
     Suppliers
    1.27
    component
    1.27
     parts
    1.24
    Activations Density 0.032%

    No Known Activations