© 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. 10829
    Prev
    Next
    INDEX
    Explanations

    book numbers, stacking

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

    The neuron specializes in spotting standalone numeric values—especially decimal numbers or measurements—embedded in the text.

    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
     you
    -2.33
    外の
    -1.88
    
    -1.76
     universite
    -1.71
     ona
    -1.70
    铪
    -1.67
    ᕱ
    -1.66
    鼍
    -1.66
    ᐠ
    -1.63
     meur
    -1.61
    POSITIVE LOGITS
    ⑉
    1.91
    We
    1.90
    am
    1.87
     Entste
    1.87
     books
    1.81
     successivo
    1.81
    I
    1.80
    with
    1.78
    From
    1.78
    Additionally
    1.76
    Activations Density 0.048%

    No Known Activations