© 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. 21406
    Prev
    Next
    INDEX
    Explanations

    email addresses and names

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

    The neuron fires on any token containing numeric digits (i.e. number sequences).

    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
     Their
    -1.38
    盉
    -1.34
    honestly
    -1.30
    xvi
    -1.29
     gewor
    -1.27
     각
    -1.27
     decidió
    -1.26
     nimmer
    -1.25
    乆
    -1.24
     automó
    -1.23
    POSITIVE LOGITS
     in
    1.75
    。。。。
    1.50
     blatantly
    1.41
     relentlessly
    1.39
     provide
    1.36
     give
    1.35
     would
    1.34
     quicker
    1.33
     dagens
    1.32
     meticulously
    1.30
    Activations Density 0.085%

    No Known Activations