© 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. 33597
    Prev
    Next
    INDEX
    Explanations

    defining lists or queries

    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
     your
    -2.83
     you
    -2.64
     YOUR
    -1.55
     yourself
    -1.48
     we
    -1.45
     вами
    -1.33
     recommended
    -1.33
    你就
    -1.29
     Your
    -1.27
     você
    -1.27
    POSITIVE LOGITS
    开发者
    1.50
     my
    1.39
     开发
    1.34
    Each
    1.23
     bijvoorbeeld
    1.20
     certaine
    1.20
     certain
    1.19
    とある
    1.17
     antaranya
    1.17
     אני
    1.17
    Activations Density 4.463%

    No Known Activations