© 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. 12159
    Prev
    Next
    INDEX
    Explanations

    frequency synthesizers

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

    The neuron primarily detects numeric and measurement tokens (e.g. digits, frequencies, units, model numbers) in technical or specification 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
     revolt
    -0.87
    ining
    -0.72
     kills
    -0.70
     LL
    -0.69
    kills
    -0.68
    稼
    -0.66
     gagné
    -0.65
     testigo
    -0.65
     رجل
    -0.64
     đưa
    -0.64
    POSITIVE LOGITS
     measurement
    1.30
     measurements
    1.12
    Measurement
    1.02
    measurement
    1.00
     Measurement
    0.96
    Meas
    0.94
     stimulus
    0.86
     BER
    0.86
     instrument
    0.84
     Meas
    0.84
    Activations Density 0.024%

    No Known Activations