© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10647
    Prev
    Next
    INDEX
    Explanations

    birth and death dates

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

    The neuron strongly activates on numeric tokens that are part of multi-digit years (date components).

    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
    φων
    -1.35
     châssis
    -1.30
     Bré
    -1.21
     fournisseurs
    -1.20
     unicornio
    -1.16
    的态度
    -1.15
     vélo
    -1.15
    ENES
    -1.14
     nasz
    -1.14
    </h1>
    -1.13
    POSITIVE LOGITS
     in
    1.39
     */
    1.22
     In
    1.19
    In
    1.17
     On
    1.14
     who
    1.13
     those
    1.13
     whose
    1.12
     which
    1.09
    ,"
    1.09
    Activations Density 0.065%

    No Known Activations