© 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. 34-GEMMASCOPE-RES-131K
    7. 8380
    Prev
    Next
    INDEX
    Explanations

    radio communication devices

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

    The neuron strongly activates on formal technical infrastructure terms—especially “system,” “radio,” “communication,” and related words describing secure or multiple-channel network setups.

    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
    requestFocus
    -0.81
     HDF
    -0.79
    Disliked
    -0.78
    Kval
    -0.77
    antino
    -0.71
     griega
    -0.71
    powiedz
    -0.71
    róż
    -0.70
    bingen
    -0.69
     BSD
    -0.69
    POSITIVE LOGITS
    Motorola
    0.92
     radios
    0.91
     radio
    0.91
     Motorola
    0.91
     trun
    0.84
     accessories
    0.83
     fleet
    0.79
     Accessories
    0.78
    Accessories
    0.78
     channel
    0.75
    Activations Density 0.007%

    No Known Activations