© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30164
    Prev
    Next
    INDEX
    Explanations

    roommate and shared living spaces

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

    The neuron is primarily detecting mentions of “room” and “roommate” (i.e. tokens related to rooms or roommates).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     fehlen
    -0.80
     poffible
    -0.74
     bỏ
    -0.74
    Playground
    -0.73
    ghold
    -0.71
    拢
    -0.70
    hpur
    -0.70
     yılında
    -0.69
     grandchildren
    -0.69
    OKU
    -0.68
    POSITIVE LOGITS
     roommate
    4.72
     roommates
    4.56
     Room
    2.09
     room
    2.08
    room
    2.05
    Room
    1.91
     ROOM
    1.90
     apartment
    1.83
    ROOM
    1.63
    eroom
    1.54
    Activations Density 0.037%

    No Known Activations