© 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. 66277
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
     هفت
    -0.70
     szczególnie
    -0.70
    ジャン
    -0.68
    द्य
    -0.67
     similar
    -0.66
    Each
    -0.66
     against
    -0.65
     each
    -0.65
    argue
    -0.65
    ApiService
    -0.64
    POSITIVE LOGITS
    èces
    0.80
    onges
    0.80
     Rights
    0.80
     Sprache
    0.79
     lola
    0.77
    seudo
    0.76
    getResource
    0.75
    分离
    0.75
     Selected
    0.75
    ニング
    0.73
    Activations Density 0.031%

    No Known Activations