© 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. 11374
    Prev
    Next
    INDEX
    Explanations

    value counts

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

    This neuron activates specifically on the word “counts.”

    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
    yskland
    -3.09
    ſam
    -3.05
    g
    -2.80
    ⡪
    -2.78
    푙
    -2.70
    鴆
    -2.58
    鱚
    -2.52
    쫑
    -2.50
    ㆆ
    -2.50
    鯪
    -2.50
    POSITIVE LOGITS
     
    3.48
    '
    2.94
    Initially
    2.80
    During
    2.56
    。。。。
    2.52
    可以
    2.50
      
    2.50
    Since
    2.42
    ：　
    2.38
    This
    2.34
    Activations Density 0.004%

    No Known Activations