© 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. 48056
    Prev
    Next
    INDEX
    Explanations

    university names and associated institutions

    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
     their
    -1.75
    Their
    -1.59
    の方も
    -1.48
    EDAD
    -1.39
     nueva
    -1.39
     philosophical
    -1.35
     nuovi
    -1.32
    ọc
    -1.31
     aqueles
    -1.30
    きれい
    -1.26
    POSITIVE LOGITS
    \_
    1.58
    9
    1.51
     \_
    1.51
    ]){
    1.49
    "><!--
    1.47
     \&
    1.45
    kę
    1.45
     =
    1.45
    ではでは
    1.43
     $=$
    1.38
    Activations Density 0.022%

    No Known Activations