© 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. 136
    Prev
    Next
    INDEX
    Explanations

    often,

    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
     and
    -2.63
    兹
    -1.77
     zout
    -1.70
     lijn
    -1.65
     is
    -1.64
    摑
    -1.59
    秕
    -1.57
    oneer
    -1.56
    quate
    -1.54
    erea
    -1.52
    POSITIVE LOGITS
    蕷
    1.96
     людей
    1.76
     pengurus
    1.75
     benötigt
    1.52
     zweite
    1.48
    情况下
    1.47
    ໊
    1.43
     pensato
    1.41
     друж
    1.41
     dasarnya
    1.40
    Activations Density 0.012%

    No Known Activations