© 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. 10-GEMMASCOPE-RES-131K
    7. 99134
    Prev
    Next
    INDEX
    Explanations

    living room, living space

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

    The neuron fires on mentions of “living” (often paired with room, area, space, or dining) as in real-estate descriptions of living rooms or living areas.

    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
     ESTADO
    -1.66
    姤
    -1.56
     episódios
    -1.55
    訁
    -1.53
     to
    -1.53
    afficher
    -1.52
     spesifik
    -1.52
     feitas
    -1.47
     diction
    -1.46
     Eylül
    -1.46
    POSITIVE LOGITS
     \
    1.70
     Careful
    1.66
     //
    1.59
    大幅
    1.51
     konnten
    1.50
     \\
    1.45
    fromUtf
    1.44
     stringent
    1.43
     /
    1.43
     one
    1.43
    Activations Density 0.005%

    No Known Activations