© 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. 82515
    Prev
    Next
    INDEX
    Explanations

    names and technical terms

    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
    Though
    -1.48
    Although
    -1.39
    During
    -1.34
     through
    -1.34
     Though
    -1.33
    While
    -1.31
     during
    -1.31
    Through
    -1.27
     During
    -1.23
     in
    -1.22
    POSITIVE LOGITS
     goofy
    1.38
     direc
    1.28
     shimmering
    1.23
     ridiculously
    1.19
     pivotal
    1.17
     amazingly
    1.15
     wonderfully
    1.14
     alluring
    1.13
     wacky
    1.12
     crappy
    1.10
    Activations Density 0.000%

    No Known Activations