© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1509
    Prev
    Next
    INDEX
    Explanations

    housing descriptions with bedroom counts

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

    The neuron fires most strongly on numerical mentions of bedroom counts (e.g. “2 bedroom,” “3 bedroom,” etc.) in real-estate listing 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_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
     similar
    -1.06
    _,
    -0.95
     four
    -0.95
     suchte
    -0.91
     similarly
    -0.91
     dichi
    -0.90
     FOUR
    -0.90
    :{
    -0.87
     Bezug
    -0.87
    four
    -0.86
    POSITIVE LOGITS
     with
    1.98
     in
    1.32
     apartment
    1.22
     плюс
    1.20
     plus
    1.14
     PLUS
    0.94
     condo
    0.93
    ҟ
    0.92
     near
    0.90
    leyebilirsiniz
    0.89
    Activations Density 0.013%

    No Known Activations