© 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. 9571
    Prev
    Next
    INDEX
    Explanations

    headings and lists

    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
     any
    -1.64
     this
    -1.63
     its
    -1.55
     even
    -1.52
     people
    -1.45
     many
    -1.42
     in
    -1.39
     other
    -1.38
     more
    -1.33
     also
    -1.30
    POSITIVE LOGITS
    selben
    1.34
    
    1.22
    Katalog
    1.20
     DIFFERENT
    1.18
     trám
    1.16
    Traducción
    1.16
    튿
    1.15
    keeps
    1.13
     parlement
    1.12
    Ruju
    1.10
    Activations Density 0.001%

    No Known Activations