© 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. 34-GEMMASCOPE-RES-131K
    7. 65292
    Prev
    Next
    INDEX
    Explanations

    numbers followed by pages

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

    The neuron activates on numeric specifications (numbers, numeric limits, and measurement expressions).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     SOME
    -0.84
     BaseActivity
    -0.82
     крайней
    -0.82
    tisan
    -0.73
    smallskip
    -0.72
    нием
    -0.69
    acb
    -0.69
    BaseActivity
    -0.68
    begingroup
    -0.68
    sej
    -0.68
    POSITIVE LOGITS
     pages
    3.19
     page
    3.19
    page
    2.47
    Page
    2.25
     Page
    2.14
     Pages
    2.08
    pages
    2.08
     página
    1.87
     paragraph
    1.80
    Pages
    1.80
    Activations Density 0.035%

    No Known Activations