© 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. 82243
    Prev
    Next
    INDEX
    Explanations

    analyzed, determined, predicted

    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
    至尊
    -0.94
    很赞
    -0.94
     dilaporkan
    -0.91
    ʶ
    -0.89
     whitish
    -0.89
     curieux
    -0.88
     doggy
    -0.88
    cím
    -0.85
     bluish
    -0.85
    pronounced
    -0.84
    POSITIVE LOGITS
     research
    1.20
     researching
    1.15
     researched
    1.13
     scholars
    1.04
     indicators
    1.02
     coordinates
    1.00
     shortcomings
    0.98
     changes
    0.96
     premise
    0.95
    ByPrimaryKey
    0.95
    Activations Density 0.253%

    No Known Activations