© 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. 123760
    Prev
    Next
    INDEX
    Explanations

    smaller, lighter, quieter, thinner

    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
     
    -1.40
     Alguns
    -1.31
     Capacidad
    -1.27
     Também
    -1.24
     Talvez
    -1.20
     Porém
    -1.20
     espressione
    -1.20
     Años
    -1.20
    我知道
    -1.20
     Ainda
    -1.20
    POSITIVE LOGITS
     and
    1.53
     bygge
    1.48
     Kategorie
    1.38
    tahan
    1.27
    ↰
    1.25
    ;*/
    1.24
    "],
    
    1.23
    ,-\
    1.21
     dioxide
    1.20
     utan
    1.20
    Activations Density 0.045%

    No Known Activations