© 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. 34-GEMMASCOPE-RES-131K
    4. 107776
    Prev
    Next
    INDEX
    Explanations

    mattresses and luxurious bedding

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

    The neuron strongly activates on mentions of bedding and mattress‐related product terms (e.g. mattress, pillow, foam, latex, duvet).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     χω
    -0.72
     Commissioners
    -0.69
    ček
    -0.69
    裂
    -0.68
    匿名使用者
    -0.68
     Arabic
    -0.66
    zinho
    -0.66
    >+</
    -0.66
    дакти
    -0.65
     hemispheres
    -0.65
    POSITIVE LOGITS
     mattress
    2.30
     mattresses
    2.11
     Mattress
    1.52
    matt
    1.43
     memory
    1.38
     foam
    1.37
    Matt
    1.23
     beds
    1.22
    マット
    1.19
     matelas
    1.16
    Activations Density 0.021%

    No Known Activations