© 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. 97973
    Prev
    Next
    INDEX
    Explanations

    receive or get discounts

    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
    עות
    -0.86
    ByPrimaryKey
    -0.76
    RestController
    -0.75
     comparación
    -0.74
     Donations
    -0.74
    lixir
    -0.73
    valents
    -0.73
    idjan
    -0.73
    alts
    -0.72
    gery
    -0.72
    POSITIVE LOGITS
     discount
    4.25
     discounts
    3.83
     discounted
    3.25
    discount
    3.19
    Discount
    2.83
     Discounts
    2.67
     Discount
    2.67
     discounting
    2.34
    Discounts
    2.31
     reduction
    2.16
    Activations Density 0.029%

    No Known Activations