© 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. 40153
    Prev
    Next
    INDEX
    Explanations

    introduction, making, share

    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
     supremely
    -1.61
     exquisitely
    -1.49
     getting
    -1.47
     taking
    -1.47
     in
    -1.47
     unrelenting
    -1.45
     profoundly
    -1.45
     strangely
    -1.43
     dazzling
    -1.38
     Taking
    -1.38
    POSITIVE LOGITS
     debacle
    1.37
     famoso
    1.33
     soooo
    1.31
    部分が
    1.27
     amd
    1.23
    probably
    1.22
     evtl
    1.21
    
    1.20
     Mexique
    1.20
     discer
    1.19
    Activations Density 0.002%

    No Known Activations