© 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. 80921
    Prev
    Next
    INDEX
    Explanations

    partial differential

    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
    ossi
    -0.78
    ulp
    -0.75
     ymax
    -0.73
    стой
    -0.73
     maximum
    -0.72
    Organizer
    -0.72
    řeb
    -0.72
    tover
    -0.71
    ymax
    -0.71
     lâmpada
    -0.71
    POSITIVE LOGITS
     velocity
    1.02
     hydrostatic
    0.95
     salinity
    0.89
    TokenNameLBRACE
    0.87
    Velocity
    0.87
     öv
    0.85
    Temperature
    0.83
    Potential
    0.82
     trypsin
    0.82
     velocities
    0.81
    Activations Density 0.006%

    No Known Activations