© 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. 22-GEMMASCOPE-RES-131K
    4. 13442
    Prev
    Next
    INDEX
    Explanations

    pronouns and names as subjects

    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
     after
    -1.34
     because
    -1.34
     other
    -1.27
     mainly
    -1.26
     would
    -1.26
     sometimes
    -1.24
     in
    -1.23
     terapi
    -1.21
     разные
    -1.21
     especias
    -1.20
    POSITIVE LOGITS
    што
    1.23
     Tasse
    1.22
    курен
    1.21
    XMLSchema
    1.16
    虽
    1.16
    鋅
    1.16
    的气息
    1.15
    ꓕ
    1.15
    “
    1.15
    же
    1.13
    Activations Density 0.059%

    No Known Activations