© 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. 103099
    Prev
    Next
    INDEX
    Explanations

    variety, wine, vineyard, vintage

    np_acts-logits-general · gemini-2.5-flash-lite

    names of publications like "Variety" and words related to vines and wineries.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ricorn
    -0.81
    minecraftforge
    -0.78
     quarry
    -0.73
    kovic
    -0.73
     Sergio
    -0.71
    PA
    -0.69
    drop
    -0.69
     Corsica
    -0.67
     locate
    -0.66
    velser
    -0.66
    POSITIVE LOGITS
     atmósfera
    0.86
    gars
    0.84
    gary
    0.83
    yard
    0.79
    YARD
    0.77
     muerta
    0.76
    tambah
    0.76
    ~=
    0.74
    Vine
    0.73
    OCUS
    0.73
    Activations Density 0.028%

    No Known Activations