© 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. 11210
    Prev
    Next
    INDEX
    Explanations

    communication rates and speeds

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

    units of data transfer speed or rate, particularly megabits per second (Mbps) and kilobits per second (kbps).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects mentions of data‐throughput measurements (e.g., Mbps, kb/s).

    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
    媜
    -2.28
    ☫
    -2.06
    庒
    -2.02
    鼕
    -1.92
     also
    -1.88
     fashioned
    -1.84
    ꒥
    -1.76
    尛
    -1.72
    饜
    -1.70
     croce
    -1.66
    POSITIVE LOGITS
    O
    1.85
    ه
    1.70
     ausschließlich
    1.59
    ،
    1.56
    我們
    1.56
    Remember
    1.52
    可以
    1.49
    from
    1.48
     Когда
    1.45
    戗
    1.45
    Activations Density 0.005%

    No Known Activations