© 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. 22-GEMMASCOPE-RES-131K
    7. 54544
    Prev
    Next
    INDEX
    Explanations

    quotation marks and "inspired"

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

    This neuron fires on quantitative information—tokens conveying numerical or measurable data (numbers, units, and related context).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    もありました
    -0.98
     />
    -0.97
    月に
    -0.91
    ]
    -0.90
    uksia
    -0.88
    esistenza
    -0.87
     机械
    -0.86
     reportedly
    -0.86
     statunitense
    -0.85
     piatta
    -0.85
    POSITIVE LOGITS
     "
    1.93
     “
    1.83
     ‘
    1.32
     '
    1.27
     „
    1.20
    possibly
    1.08
    probably
    1.07
     "...
    1.02
    mainly
    1.00
    Inspired
    0.99
    Activations Density 0.051%

    No Known Activations