© 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. 93072
    Prev
    Next
    INDEX
    Explanations

    this + category/type

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron responds to demonstrative determiners, particularly “this” and “these.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     turisti
    -1.13
     viață
    -1.08
    various
    -1.02
    etui
    -1.02
    Aler
    -1.02
     generó
    -1.01
     toată
    -1.01
     字母
    -1.01
     手工
    -1.00
    superdry
    -1.00
    POSITIVE LOGITS
     category
    1.77
     section
    1.57
     option
    1.43
     this
    1.38
     component
    1.34
     segment
    1.29
     area
    1.28
     part
    1.18
     opción
    1.17
     module
    1.14
    Activations Density 0.016%

    No Known Activations