© 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. 85083
    Prev
    Next
    INDEX
    Explanations

    fish and star-like particles

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

    names of transportation routes and infrastructure, such as highways, railways, and waterways.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on mentions of named transportation corridors—highways, rail lines, trails, and other route names.

    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
     パソコン
    -1.66
    rógeno
    -1.63
    屣
    -1.58
     cimetière
    -1.55
     -"
    -1.55
    ۱
    -1.52
    umlu
    -1.50
    奁
    -1.50
     wako
    -1.48
     boister
    -1.48
    POSITIVE LOGITS
     and
    1.77
     in
    1.36
     under
    1.34
     also
    1.34
    럽
    1.31
     детьми
    1.22
    J
    1.22
     or
    1.21
     infiltration
    1.21
     while
    1.19
    Activations Density 0.066%

    No Known Activations