© 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. 29094
    Prev
    Next
    INDEX
    Explanations

    names ending in ioma or ovich/owd / words related to Mesa or plan

    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
    
    -1.78
     from
    -1.46
     only
    -1.46
     pouze
    -1.42
     ONLY
    -1.42
    沨
    -1.35
    сибир
    -1.35
     somente
    -1.34
    alted
    -1.32
     seleccionamos
    -1.31
    POSITIVE LOGITS
    on
    1.62
     that
    1.50
    他
    1.45
    找
    1.43
    M
    1.42
    苼
    1.40
    os
    1.40
    op
    1.39
    ০
    1.39
    begin
    1.36
    Activations Density 0.127%

    No Known Activations