© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83846
    Prev
    Next
    INDEX
    Explanations

    transitory and fleeting concepts

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

    The neuron detects words or word‐parts that convey ephemerality or fleeting, transient qualities.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    摀
    -2.69
    ఽ
    -2.64
    
    -2.55
    迓
    -2.38
     famed
    -2.33
    
    -2.33
    傒
    -2.31
    を見ながら
    -2.28
     renowned
    -2.27
    襁
    -2.25
    POSITIVE LOGITS
    '
    3.52
    n
    3.30
     Surprisingly
    2.77
     There
    2.59
     Getting
    2.50
     Despite
    2.44
     Trying
    2.42
     Ironically
    2.42
     Because
    2.34
     Going
    2.34
    Activations Density 0.003%

    No Known Activations