© 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. 34-GEMMASCOPE-RES-131K
    7. 65774
    Prev
    Next
    INDEX
    Explanations

    situated very close

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

    This neuron detects terms and phrases typical of real estate listings—like property types, home features, and location descriptions.

    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
    ">*</
    -1.13
    abinieri
    -1.12
     verschillende
    -0.96
    譏
    -0.93
     invece
    -0.93
     zabud
    -0.92
    
    -0.92
     באמצעות
    -0.91
     darunter
    -0.89
    tais
    -0.89
    POSITIVE LOGITS
     close
    3.34
     minutes
    2.58
     near
    2.39
     just
    2.22
     within
    2.13
    close
    2.09
     only
    2.00
     Close
    1.95
    Close
    1.94
     seconds
    1.88
    Activations Density 0.044%

    No Known Activations