© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65843
    Prev
    Next
    INDEX
    Explanations

    events and entities established

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

    The neuron is strongly activated by numeric tokens—especially years, dates, and other digit sequences indicating chronological or numerical data.

    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
     recently
    -1.71
    Recently
    -1.39
     Recently
    -1.38
     récemment
    -1.35
     lately
    -1.35
     recientemente
    -1.30
     prossima
    -1.23
    Proč
    -1.17
     cuando
    -1.16
    最近
    -1.16
    POSITIVE LOGITS
     immediately
    1.59
     сразу
    1.35
     instantly
    1.27
     lendemain
    1.20
    immediately
    1.17
     immedi
    1.14
    鹦
    1.13
    ficial
    1.12
    PostConstruct
    1.11
     verbe
    1.10
    Activations Density 0.075%

    No Known Activations