© 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. 123993
    Prev
    Next
    INDEX
    Explanations

    idea or concept of

    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
     still
    -1.54
     now
    -1.45
     with
    -1.42
     those
    -1.41
     on
    -1.41
     his
    -1.30
    ierra
    -1.28
     list
    -1.25
     r
    -1.23
     here
    -1.23
    POSITIVE LOGITS
    
    1.54
    werten
    1.48
     навіть
    1.45
    springen
    1.43
     雲
    1.41
    🙀
    1.38
     vermel
    1.38
     endast
    1.34
    вної
    1.33
     μόνο
    1.32
    Activations Density 0.113%

    No Known Activations