© 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. 81725
    Prev
    Next
    INDEX
    Explanations

    cards, suits, and replacement

    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
    mittance
    -1.03
    iphery
    -0.90
    inosau
    -0.90
    insel
    -0.82
     Hierro
    -0.82
    쿡
    -0.81
    anair
    -0.80
     Ziele
    -0.80
    jší
    -0.79
    antado
    -0.79
    POSITIVE LOGITS
     cards
    2.80
     card
    2.78
     Card
    1.80
    cards
    1.80
     Cards
    1.78
    Card
    1.73
    Cards
    1.73
    card
    1.70
    牌
    1.65
     CARDS
    1.61
    Activations Density 0.014%

    No Known Activations