© 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. 9709
    Prev
    Next
    INDEX
    Explanations

    bed and related objects

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

    The neuron primarily detects mentions of “bed” (and its plural “beds”) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    content
    -1.25
    Опыт
    -1.20
    AJAX
    -1.18
    ischem
    -1.17
    ge
    -1.16
    而
    -1.15
     stabilis
    -1.14
     religios
    -1.13
    品的
    -1.13
     practi
    -1.12
    POSITIVE LOGITS
     bed
    1.46
     blankets
    1.28
     моя
    1.24
    轎
    1.21
     sleep
    1.18
     beds
    1.18
    sleeping
    1.17
     mattress
    1.14
    Selección
    1.14
     nights
    1.13
    Activations Density 0.042%

    No Known Activations