© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118168
    Prev
    Next
    INDEX
    Explanations

    restoration and modification of buildings

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

    The neuron fires strongly on detailed chronological or historical descriptions of a building’s construction, repairs, and other timeline events.

    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
     مناط
    -1.03
     оружи
    -0.99
     websites
    -0.94
     bikin
    -0.93
     kaynağından
    -0.93
     ehemalige
    -0.91
     their
    -0.90
     wuß
    -0.90
    ranno
    -0.90
    Www
    -0.90
    POSITIVE LOGITS
     restoration
    1.20
     damage
    1.11
     rebuilding
    1.10
     repairs
    1.09
     reconstruction
    1.06
     interventions
    1.01
     alterations
    0.99
    改
    0.97
     additions
    0.97
     funds
    0.97
    Activations Density 0.056%

    No Known Activations