© 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. 10-GEMMASCOPE-RES-131K
    7. 20463
    Prev
    Next
    INDEX
    Explanations

    temporal seasons and years

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

    The neuron detects numeric tokens denoting seasons, years, or other date-related figures.

    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
    ście
    -1.24
     dorado
    -1.23
    鬓
    -1.18
    \\
    -1.17
    他已经
    -1.16
     сегодняшний
    -1.15
     delà
    -1.11
    aud
    -1.10
     ומש
    -1.10
    mic
    -1.08
    POSITIVE LOGITS
     coloridos
    1.20
     According
    1.18
     this
    1.18
     Zeugen
    1.18
    графии
    1.17
     Grundlage
    1.16
    osexuality
    1.15
    ників
    1.14
     seguras
    1.13
     marcadas
    1.12
    Activations Density 0.057%

    No Known Activations