© 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. 34-GEMMASCOPE-RES-131K
    7. 118765
    Prev
    Next
    INDEX
    Explanations

    product sizes and volumes

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

    The neuron strongly activates on numeric values and associated measurement units (e.g. dosages, volumes).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     gehören
    -0.83
     add
    -0.80
     they
    -0.79
    sihan
    -0.79
    b
    -0.78
     assured
    -0.75
     assist
    -0.74
     dicembre
    -0.73
    spaceBetween
    -0.73
    ]**
    -0.71
    POSITIVE LOGITS
     size
    1.35
     pack
    1.33
     sizes
    1.26
     jar
    1.19
     bottle
    1.16
    größe
    1.11
    larger
    1.11
    Inhoud
    1.09
     ขนาด
    1.06
    Size
    1.05
    Activations Density 0.019%

    No Known Activations