© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60634
    Prev
    Next
    INDEX
    Explanations

    almost or nearly quantities

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

    The neuron predominantly responds to numeric expressions (counts, measurements, and statistics) 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
            
    -1.80
          
    -1.63
     The
    -1.59
    一方で
    -1.55
    すぐに
    -1.49
     ie
    -1.44
     Damit
    -1.42
     Also
    -1.41
     and
    -1.41
     I
    -1.40
    POSITIVE LOGITS
     was
    2.17
     lienzo
    1.81
    onomies
    1.80
     nuovi
    1.73
     autocollant
    1.70
    眎
    1.68
    就是
    1.66
    縯
    1.59
    amblea
    1.59
    ⓿
    1.57
    Activations Density 0.027%

    No Known Activations