© 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. 48260
    Prev
    Next
    INDEX
    Explanations

    compared with

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

    The neuron strongly activates on numerical values, statistical comparisons, and “compared with”-style quantitative phrases.

    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
     first
    -1.57
    是非常
    -1.52
    还未
    -1.51
     appré
    -1.42
     kök
    -1.41
    細節
    -1.40
     أيض
    -1.39
    Lleg
    -1.38
     conster
    -1.38
     réinitial
    -1.37
    POSITIVE LOGITS
     if
    1.66
     with
    1.36
    骇
    1.29
    ers
    1.28
     in
    1.27
    𝓰
    1.24
    giarism
    1.22
    </b>
    1.21
    Cartesian
    1.21
     menyambut
    1.20
    Activations Density 0.378%

    No Known Activations