© 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. 69250
    Prev
    Next
    INDEX
    Explanations

    remains to be seen or need to

    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
    róleo
    -1.45
     continuant
    -1.41
    時点で
    -1.36
     apparence
    -1.34
     projets
    -1.33
    ревно
    -1.31
    
    -1.31
    </sup>
    -1.31
     acheter
    -1.27
    rifts
    -1.27
    POSITIVE LOGITS
     najdete
    1.52
     It
    1.51
     improve
    1.29
     learn
    1.28
     asses
    1.25
     find
    1.24
     need
    1.21
     unic
    1.20
    あとは
    1.20
     time
    1.18
    Activations Density 0.031%

    No Known Activations