© 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. 49631
    Prev
    Next
    INDEX
    Explanations

    technology sectors

    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
     montañas
    -0.98
     verkauft
    -0.95
     ruinas
    -0.94
    Życiorys
    -0.90
     ocasiones
    -0.90
     целью
    -0.90
     faldas
    -0.88
    Véase
    -0.88
    hdysval
    -0.86
     the
    -0.86
    POSITIVE LOGITS
     adoption
    1.54
     technologies
    1.52
     implementation
    1.51
     applications
    1.48
     technology
    1.39
     implementación
    1.23
     solutions
    1.23
     initiatives
    1.22
     concept
    1.18
     devices
    1.15
    Activations Density 0.152%

    No Known Activations