© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84528
    Prev
    Next
    INDEX
    Explanations

    various items, goods, or products

    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
     one
    -1.80
     in
    -1.62
     or
    -1.59
     on
    -1.52
     only
    -1.40
     activities
    -1.35
     as
    -1.27
     when
    -1.26
     people
    -1.24
     the
    -1.23
    POSITIVE LOGITS
     allerlei
    1.29
     maksi
    1.27
     galeri
    1.27
    瞜
    1.27
     seksi
    1.26
     rapor
    1.25
     renfer
    1.24
    THERE
    1.24
     diverses
    1.23
     profili
    1.23
    Activations Density 0.041%

    No Known Activations