© 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. 10-GEMMASCOPE-RES-131K
    7. 127393
    Prev
    Next
    INDEX
    Explanations

    County and Appeals court decisions

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

    The neuron is triggered by mentions of county names or references to “County” in location labels.

    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
     our
    -1.45
     bacio
    -1.30
     someone
    -1.29
    ふう
    -1.28
     treno
    -1.24
    也會
    -1.24
     dévelo
    -1.23
     umfang
    -1.23
     beschäf
    -1.22
     tecnica
    -1.22
    POSITIVE LOGITS
    ."
    1.44
    ("
    1.30
     notamment
    1.25
    蚕
    1.20
    。
    1.19
    ktionen
    1.18
     reindeer
    1.09
    кожа
    1.09
     FEBRUARY
    1.09
    ших
    1.09
    Activations Density 0.482%

    No Known Activations