© 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. 71210
    Prev
    Next
    INDEX
    Explanations

    ideal; ideals; idealistic

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

    The neuron activates on occurrences of “ideal” and its variants (ideals, idealistic, ideological) in the text.

    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
    獃
    -2.25
    他还
    -1.95
    婠
    -1.84
    
    -1.83
     stings
    -1.77
     {},
    -1.75
    来自于
    -1.73
    ",
    -1.72
    uttgart
    -1.71
    %">
    -1.71
    POSITIVE LOGITS
    {
    2.72
    0
    2.09
     ideals
    1.95
    4
    1.85
    𓍊
    1.79
     dvi
    1.73
     innego
    1.70
     meres
    1.69
    ﹍﹍
    1.64
    VISED
    1.63
    Activations Density 0.003%

    No Known Activations