© 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. 9619
    Prev
    Next
    INDEX
    Explanations

    constant value

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

    The neuron strongly activates on occurrences of the word “constant.”

    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
     !!!!!
    -3.02
     decidedly
    -2.80
     dando
    -2.78
    푏
    -2.73
     .........
    -2.70
    ⧠
    -2.66
     delectable
    -2.66
     !!!!
    -2.64
     .......
    -2.58
    
    -2.56
    POSITIVE LOGITS
    With
    3.09
    ～　
    3.03
     provide
    2.91
     meticulously
    2.86
    _;
    2.80
     primarily
    2.78
     ostensibly
    2.77
    ～。
    2.75
    ～♪
    2.73
     considerable
    2.72
    Activations Density 0.009%

    No Known Activations