© 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. 10-GEMMASCOPE-RES-131K
    4. 47468
    Prev
    Next
    INDEX
    Explanations

    increasing or decreasing over time

    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
     must
    -1.33
    是一個
    -1.24
    他们
    -1.23
    meyen
    -1.23
    They
    -1.20
    他們
    -1.20
     azonban
    -1.20
     apartament
    -1.15
     should
    -1.14
     kaikki
    -1.14
    POSITIVE LOGITS
     to
    1.96
     by
    1.54
     in
    1.40
     due
    1.19
     it
    1.19
     toward
    1.14
     überweisen
    1.13
     the
    1.12
     into
    1.12
    になっている
    1.10
    Activations Density 0.316%

    No Known Activations