© 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. 10-GEMMASCOPE-RES-131K
    7. 1302
    Prev
    Next
    INDEX
    Explanations

    legal entities and locations

    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_10/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
     puedes
    -1.73
     didn
    -1.72
     start
    -1.70
     are
    -1.63
     starts
    -1.61
     tell
    -1.59
     suggest
    -1.59
     trying
    -1.58
     about
    -1.57
    ࿚
    -1.53
    POSITIVE LOGITS
    Beschrijving
    1.69
     pertumbuhan
    1.68
     his
    1.66
    🤓
    1.65
     reizen
    1.65
    ‼
    1.63
    imetry
    1.60
    らせる
    1.59
    rrrrrrrr
    1.57
     wandel
    1.56
    Activations Density 0.523%

    No Known Activations