© 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. 22-GEMMASCOPE-RES-131K
    7. 130100
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily triggered by numeric tokens (especially multi‐digit year values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    temporal progression and duration

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     bereits
    -1.14
     longstanding
    -1.04
     for
    -1.00
    分で
    -0.99
     शुर
    -0.98
     HUGE
    -0.98
     new
    -0.96
     berusia
    -0.96
    atividade
    -0.95
     by
    -0.93
    POSITIVE LOGITS
     then
    1.45
    期间
    1.20
     continually
    1.12
     eventually
    1.05
     longest
    1.05
    eron
    1.04
     finally
    1.03
    eventually
    1.03
     thereafter
    1.01
    during
    0.99
    Activations Density 0.085%

    No Known Activations