© 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. 10-GEMMASCOPE-RES-131K
    7. 105669
    Prev
    Next
    INDEX
    Explanations

    ability to

    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
     they
    -2.00
     их
    -1.59
     of
    -1.59
     ellos
    -1.52
     ними
    -1.44
    t
    -1.40
     them
    -1.38
    n
    -1.38
    They
    -1.38
     آن‌ها
    -1.38
    POSITIVE LOGITS
     and
    1.41
    baliknya
    1.35
     or
    1.30
     första
    1.24
    cepat
    1.23
    thiet
    1.21
    fatter
    1.20
    akhir
    1.20
     chaussures
    1.19
    咱们
    1.18
    Activations Density 0.211%

    No Known Activations