© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90649
    Prev
    Next
    INDEX
    Explanations

    archive/metadata/field

    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
    ニ
    -1.10
     have
    -1.09
     республи
    -1.07
    CardHeader
    -1.05
    	
    -1.05
     і
    -1.03
    なさ
    -1.03
     which
    -1.02
     (
    -1.02
     seine
    -1.01
    POSITIVE LOGITS
     cũng
    1.32
     też
    1.29
     facili
    1.28
     jestem
    1.26
     arī
    1.23
     Also
    1.23
     også
    1.23
     OVERVIEW
    1.20
     Также
    1.20
     Privac
    1.20
    Activations Density 0.017%

    No Known Activations