© 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. 22-GEMMASCOPE-RES-131K
    7. 39501
    Prev
    Next
    INDEX
    Explanations

    company and location names

    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_22/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
     vividly
    -1.88
     powerfully
    -1.85
     emphatically
    -1.83
     brimming
    -1.81
     brilliantly
    -1.77
     escalating
    -1.77
     intelligently
    -1.75
     disregarding
    -1.74
     hopelessly
    -1.73
     stubbornly
    -1.73
    POSITIVE LOGITS
     литров
    1.59
    散文
    1.57
    思念
    1.52
    祈祷
    1.49
    ꯭
    1.41
    ٗ
    1.34
    呪術
    1.28
    Those
    1.27
    曲は
    1.27
    髑
    1.23
    Activations Density 29.262%

    No Known Activations