© 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. 42114
    Prev
    Next
    INDEX
    Explanations

    carry or stock offerings

    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
    ↵
    -1.45
      
    -1.42
    "
    -1.33
    icherheit
    -1.32
     Eğer
    -1.30
    šan
    -1.21
    -1.15
    (
    -1.13
     edific
    -1.11
    				
    -1.11
    POSITIVE LOGITS
     them
    1.32
     perkembangan
    1.27
     realizando
    1.27
    有不
    1.23
    ését
    1.21
     紹介
    1.21
    IZABETH
    1.20
    notic
    1.20
    Información
    1.19
    vám
    1.19
    Activations Density 0.037%
    No Known Activations