© 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. 10-GEMMASCOPE-RES-131K
    4. 85227
    Prev
    Next
    INDEX
    Explanations

    radio communication and dispatch

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

    The neuron activates on mentions of radio or wireless communication technologies and devices (e.g. “radio,” “communications,” “network,” “walkie-talkie”).

    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
     acoged
    -1.50
     protegida
    -1.41
     cómoda
    -1.40
    masalah
    -1.37
     wußte
    -1.35
    ̼
    -1.34
    のかもしれません
    -1.34
     geprü
    -1.33
     tych
    -1.31
     funktioner
    -1.30
    POSITIVE LOGITS
    el
    1.62
    uously
    1.41
    __,
    1.41
    ности
    1.41
    一声
    1.40
    hest
    1.34
    auw
    1.30
    塁
    1.30
    dzić
    1.30
    )}
    1.30
    Activations Density 0.052%

    No Known Activations