© 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. 81768
    Prev
    Next
    INDEX
    Explanations

    numerical calculation or code

    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
    Finding
    -0.84
     finding
    -0.79
     aset
    -0.75
    specification
    -0.74
     bawa
    -0.73
    finding
    -0.71
     baga
    -0.71
     حسب
    -0.71
     vaid
    -0.71
    Specification
    -0.70
    POSITIVE LOGITS
    тності
    0.84
    好好的
    0.79
    身邊
    0.77
    vable
    0.77
    unda
    0.76
    Weir
    0.76
    Willem
    0.75
     fain
    0.75
     alimentaires
    0.74
     støtte
    0.73
    Activations Density 0.029%

    No Known Activations