© 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. 74670
    Prev
    Next
    INDEX
    Explanations

    vehicle types

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

    The main thing this neuron does is detect numeric tokens indicating quantities or measurements (e.g., numbers and number‐related terms).

    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
     Tamanho
    -1.86
    从此
    -1.77
     münchen
    -1.76
    暧
    -1.73
    很赞
    -1.72
     всички
    -1.66
     estreia
    -1.63
    asthan
    -1.63
    颔
    -1.63
     choisissez
    -1.61
    POSITIVE LOGITS
     get
    2.03
    da
    1.81
     didn
    1.77
     do
    1.74
    io
    1.72
     usually
    1.72
    ja
    1.68
     find
    1.66
    ka
    1.64
     otra
    1.62
    Activations Density 0.110%

    No Known Activations