© 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. 66761
    Prev
    Next
    INDEX
    Explanations

    COURT OF APPEALS

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

    The neuron activates on standalone numeric tokens—especially decimal numbers—used as formatting or layout measurements rather than on ordinary words.

    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
     Because
    -2.53
     this
    -2.25
     Like
    -2.08
     our
    -2.05
     Despite
    -2.03
     However
    -2.00
     Without
    -1.95
    ৹
    -1.91
     During
    -1.90
     Although
    -1.87
    POSITIVE LOGITS
    骉
    2.20
     perspek
    1.88
    THAT
    1.84
    
    1.82
     Dinas
    1.82
    却不
    1.82
     Stanisław
    1.80
     intric
    1.79
     
    1.79
    THER
    1.76
    Activations Density 0.059%

    No Known Activations