© 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. 98454
    Prev
    Next
    INDEX
    Explanations

    wine types and descriptors

    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
    barrel
    -0.84
     vineyard
    -0.82
    Picker
    -0.77
     BIBSYS
    -0.76
    Barrel
    -0.75
     vint
    -0.74
    selective
    -0.74
     enterprises
    -0.74
     léč
    -0.73
     barrel
    -0.72
    POSITIVE LOGITS
     style
    0.89
     region
    0.88
    Everyday
    0.85
     Oregon
    0.84
     Amar
    0.84
     styles
    0.84
    χρι
    0.83
     white
    0.83
    白
    0.81
     category
    0.80
    Activations Density 0.022%

    No Known Activations