© 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. 93257
    Prev
    Next
    INDEX
    Explanations

    mathematical notation, names, scientific 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_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
     தமி
    -1.34
    ffling
    -1.26
     CheckBox
    -1.17
    Források
    -1.17
     леген
    -1.13
     Início
    -1.10
     DbType
    -1.09
     mewakili
    -1.09
     Comentarios
    -1.09
    是怎么回事
    -1.09
    POSITIVE LOGITS
     sientes
    1.14
     is
    1.13
     anything
    1.11
    Výhody
    1.09
     any
    1.07
    Filmography
    1.05
     all
    1.04
    kkelen
    1.03
    Dine
    1.03
    rías
    1.02
    Activations Density 0.007%

    No Known Activations