© 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. 74941
    Prev
    Next
    INDEX
    Explanations

    much too

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

    The neuron detects words that express quantity or degree (e.g., any, much, same, many, limited).

    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
     multifaceted
    -2.41
     exquisitely
    -2.16
     lavish
    -2.16
     enticing
    -2.13
     enables
    -2.06
     allows
    -2.06
     enhances
    -2.06
     providing
    -2.03
     invigor
    -2.03
     unrelenting
    -2.02
    POSITIVE LOGITS
     REALLY
    2.42
     VERY
    2.27
     startling
    2.19
    1
    2.11
     OVER
    2.08
    The
    2.06
     of
    1.99
     ส์
    1.98
    for
    1.94
     extravag
    1.93
    Activations Density 0.036%

    No Known Activations