© 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. 23787
    Prev
    Next
    INDEX
    Explanations

    cities and institutions

    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
     microbiome
    -1.63
     livestream
    -1.47
    ほんとに
    -1.38
     infographic
    -1.35
     uscita
    -1.26
     emoji
    -1.22
     tendrá
    -1.20
     faciliter
    -1.19
     qPCR
    -1.18
     vaping
    -1.16
    POSITIVE LOGITS
     even
    1.45
     both
    1.38
     when
    1.33
     eight
    1.33
     without
    1.32
     many
    1.31
     while
    1.29
     as
    1.29
     five
    1.28
     several
    1.27
    Activations Density 0.290%

    No Known Activations