© 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. 67279
    Prev
    Next
    INDEX
    Explanations

    in addition to

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

    The main thing this neuron does is find numeric values (quantities and measurements) 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
     itulah
    -1.58
    }>
    -1.49
     następnie
    -1.48
     there
    -1.41
     saranno
    -1.41
    AdvEx
    -1.38
     Then
    -1.34
     This
    -1.34
     atasan
    -1.33
     等
    -1.30
    POSITIVE LOGITS
     autres
    1.95
     other
    1.92
     سایر
    1.68
     autre
    1.61
     anderen
    1.59
     другим
    1.58
     outras
    1.56
    autres
    1.54
     demás
    1.54
    chenta
    1.52
    Activations Density 0.013%

    No Known Activations