© 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. 119889
    Prev
    Next
    INDEX
    Explanations

    transplantation, mutable, Dele Alli, Palo Alto, ETH

    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
     are
    -2.84
    P
    -2.83
    ,
    -2.77
    ’
    -2.56
     was
    -2.53
    ↵
    -2.34
    寢
    -2.23
     of
    -2.19
    .
    -2.19
     opens
    -2.17
    POSITIVE LOGITS
     were
    3.09
    鳧
    3.00
    棪
    2.91
     mereka
    2.69
     唯美
    2.64
    鋮
    2.55
    鮰
    2.52
    鏵
    2.52
    袮
    2.48
     έχουν
    2.47
    Activations Density 0.009%

    No Known Activations