© 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. 1701
    Prev
    Next
    INDEX
    Explanations

    furniture items

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

    The neuron responds to mentions of flat work‐surface furniture—words like “table,” “desk,” or “workstation.”

    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
    2
    -2.14
    1
    -2.06
    ㌧
    -1.54
    для
    -1.53
     artisan
    -1.53
    5
    -1.51
    3
    -1.51
     线条
    -1.51
    chris
    -1.49
    푏
    -1.48
    POSITIVE LOGITS
     what
    1.77
     same
    1.73
     recomendable
    1.64
     mismas
    1.60
    〰
    1.59
    al
    1.55
     make
    1.54
     oder
    1.54
     things
    1.52
     彼女
    1.52
    Activations Density 0.017%

    No Known Activations