© 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. 11044
    Prev
    Next
    INDEX
    Explanations

    sequence of events

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

    The neuron fires on numeric tokens—especially multi‐digit numbers and years in biographical or educational contexts.

    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
    <<<<<<<<<<<<
    -1.01
     chaque
    -0.98
     THEOREM
    -0.94
    æk
    -0.94
     lucr
    -0.93
    луй
    -0.93
    ٨
    -0.93
    starts
    -0.92
    ẩ
    -0.92
    existing
    -0.91
    POSITIVE LOGITS
     then
    1.95
     subsequently
    1.37
     went
    1.34
     later
    1.29
     następnie
    1.28
     further
    1.27
     thereafter
    1.27
     after
    1.20
    その後
    1.20
     afterward
    1.14
    Activations Density 0.056%

    No Known Activations