© 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. 66381
    Prev
    Next
    INDEX
    Explanations

    past predictions and trends

    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
     sudadera
    -1.27
     mód
    -1.23
    ysl
    -1.23
     kabát
    -1.22
    llllll
    -1.22
    튿
    -1.19
     októ
    -1.17
    Dette
    -1.14
     chaqueta
    -1.14
     cueva
    -1.12
    POSITIVE LOGITS
     when
    1.62
     of
    1.51
     from
    1.50
     now
    1.40
     in
    1.34
     like
    1.32
     after
    1.30
    y
    1.22
     through
    1.21
     before
    1.20
    Activations Density 0.021%

    No Known Activations