© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92876
    Prev
    Next
    INDEX
    Explanations

    bed, mattress, frame, headboard

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

    The neuron is specifically triggering on the compound noun “bed frame.”

    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
     seated
    -0.78
    buss
    -0.75
    omination
    -0.73
     गणना
    -0.69
    цер
    -0.69
    爍
    -0.68
     terraces
    -0.66
    venue
    -0.66
     Nieuw
    -0.66
    钥匙
    -0.66
    POSITIVE LOGITS
     headboard
    2.58
     bed
    2.20
     Bed
    1.73
    Bed
    1.65
     mattress
    1.62
    bed
    1.54
     head
    1.52
     beds
    1.52
     Head
    1.40
     BED
    1.30
    Activations Density 0.013%

    No Known Activations