© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16094
    Prev
    Next
    INDEX
    Explanations

    food and drink items

    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
     солнца
    -1.29
     or
    -1.27
     it
    -1.27
    дыду
    -1.26
     this
    -1.25
     progettazione
    -1.20
     because
    -1.19
     on
    -1.18
     through
    -1.16
     the
    -1.14
    POSITIVE LOGITS
     paillettes
    1.48
     menu
    1.44
    EVERY
    1.28
     garan
    1.27
    Offering
    1.26
     attente
    1.26
    scanning
    1.24
     назвать
    1.23
     ſever
    1.22
     bougies
    1.22
    Activations Density 0.021%

    No Known Activations