© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117595
    Prev
    Next
    INDEX
    Explanations

    radio communications

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

    The neuron strongly responds to occurrences of the word “radio” (i.e. mentions of radio or radio‐communication contexts).

    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
     Gro
    -0.81
     gro
    -0.77
     Cars
    -0.76
     peduli
    -0.72
     LG
    -0.71
    وانه
    -0.71
     kri
    -0.70
    vc
    -0.70
    哈哈哈
    -0.70
     Conservative
    -0.68
    POSITIVE LOGITS
     radio
    0.98
     radios
    0.97
     mike
    0.93
     Microphone
    0.92
    Radio
    0.91
     Ya
    0.88
     радио
    0.88
    Michel
    0.88
     rádio
    0.87
    ICOM
    0.87
    Activations Density 0.019%

    No Known Activations