© 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. 22-GEMMASCOPE-RES-131K
    7. 36208
    Prev
    Next
    INDEX
    Explanations

    imports of python libraries

    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_22/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
    lägen
    -1.05
     that
    -1.05
    また
    -1.03
    凝土
    -1.03
    optarg
    -1.03
    Sprintf
    -1.02
     blusa
    -1.02
    ctory
    -1.01
    八年
    -1.01
     eight
    -0.99
    POSITIVE LOGITS
     colorear
    1.10
     ロック
    1.05
     fabulous
    1.02
     usual
    1.02
     ulei
    1.02
    这么
    1.00
     totul
    0.97
     numele
    0.95
     déterminer
    0.95
     обы
    0.95
    Activations Density 0.001%

    No Known Activations