© 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. 98345
    Prev
    Next
    INDEX
    Explanations

    neighborhood development and community leaders

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

    The neuron is strongly activated by common, high‐frequency “generic” words (like function words and everyday nouns) and remains silent on rarer or more distinctive proper nouns.

    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
     counties
    -1.36
     Counties
    -1.17
     प्रदेश
    -1.14
     provinces
    -1.05
     province
    -1.04
    COUNTY
    -1.02
    Provincia
    -1.01
     município
    -1.00
     towns
    -0.99
     cosmopolitan
    -0.97
    POSITIVE LOGITS
     neighborhood
    3.09
     neighbourhood
    2.30
     neighbors
    2.19
     Neighborhood
    2.00
    neighborhood
    1.98
    Neighborhood
    1.90
     residents
    1.84
     NEIGH
    1.75
     neighbor
    1.74
     neighborhoods
    1.70
    Activations Density 0.058%

    No Known Activations