© 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. 34-GEMMASCOPE-RES-131K
    7. 84381
    Prev
    Next
    INDEX
    Explanations

    German, French, or other languages

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

    The neuron activates on four‐digit numerical tokens representing years (dates).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    匮
    -1.30
    ⌓
    -1.17
     such
    -1.14
    でございます
    -1.08
     сейчас
    -1.07
    tisgarh
    -1.05
    渽
    -1.05
     rusak
    -1.04
    着脸
    -1.02
    ˂
    -1.02
    POSITIVE LOGITS
    ۔
    1.07
    ⑰
    1.07
     ebenfalls
    1.03
    ette
    1.00
    ine
    0.99
     amd
    0.94
     چیه
    0.94
    ne
    0.94
     اگه
    0.94
    ville
    0.93
    Activations Density 0.093%

    No Known Activations