© 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. 105212
    Prev
    Next
    INDEX
    Explanations

    withstand pressure and time

    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
     magnético
    -1.46
    痦
    -1.38
    ată
    -1.35
    ními
    -1.35
    ornadas
    -1.32
    tissue
    -1.30
     implementar
    -1.25
     terdapat
    -1.25
    nitř
    -1.24
    ised
    -1.20
    POSITIVE LOGITS
    Its
    1.46
    ).
    1.45
    ↵
    1.41
    სქ
    1.41
    ++){
    
    1.39
     of
    1.39
     “
    1.36
    。“
    1.35
    ').
    1.34
    “,
    1.34
    Activations Density 0.014%

    No Known Activations