© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40044
    Prev
    Next
    INDEX
    Explanations

    saline, Middle, zeta, dend, full

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

    This neuron detects numeric tokens—any standalone numbers or measurement values 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_22/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
    mainly
    -1.00
     pasirink
    -0.96
    actually
    -0.94
     appliquer
    -0.94
     acheter
    -0.94
    primarily
    -0.93
     exceedingly
    -0.91
    generally
    -0.90
    NUE
    -0.90
    extremely
    -0.89
    POSITIVE LOGITS
     this
    1.32
     after
    1.16
     before
    1.16
     This
    1.07
     which
    1.07
     Before
    1.05
     would
    1.05
     blatantly
    1.04
     After
    1.03
     Since
    1.03
    Activations Density 0.120%

    No Known Activations