© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113726
    Prev
    Next
    INDEX
    Explanations

    Electron microscopic

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

    numeric characters and programming-related symbols in technical and code-related content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on tokens containing numbers (digits or numeric values, including integers and decimals).

    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
     tästä
    -1.70
     or
    -1.65
     lisäksi
    -1.62
     siihen
    -1.60
     yrity
    -1.56
     موبایل
    -1.52
     çünkü
    -1.49
     geschikt
    -1.49
     soyez
    -1.47
     then
    -1.46
    POSITIVE LOGITS
    lesssim
    1.47
     namorado
    1.42
    腟
    1.41
     fanns
    1.38
     tumbuhan
    1.35
     сахара
    1.35
     but
    1.34
     ње
    1.34
     bosques
    1.33
    𝑈
    1.33
    Activations Density 0.001%

    No Known Activations