© 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. 10-GEMMASCOPE-RES-131K
    7. 69222
    Prev
    Next
    INDEX
    Explanations

    UI actions and fields

    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_10/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
     fronteras
    -1.33
     sorprendió
    -1.27
    iramente
    -1.23
    가
    -1.23
     ます
    -1.23
     aslında
    -1.23
     hadapan
    -1.20
    ča
    -1.19
    händler
    -1.19
    ární
    -1.17
    POSITIVE LOGITS
     their
    1.85
     with
    1.49
     pères
    1.34
     их
    1.34
    tismo
    1.32
     journalistes
    1.23
    锒
    1.21
     kanilang
    1.20
     visiteurs
    1.20
    長の
    1.20
    Activations Density 0.017%

    No Known Activations