© 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. 101686
    Prev
    Next
    INDEX
    Explanations

    time ranges and periods

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

    The neuron activates chiefly on numeric tokens—especially years or other multi‐digit numbers—in the text.

    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
    >
    -1.51
    mathrm
    -1.51
     podczas
    -1.46
    9
    -1.34
    各样的
    -1.23
     very
    -1.23
    ="
    -1.23
    /***
    -1.23
     more
    -1.20
     considerable
    -1.20
    POSITIVE LOGITS
     to
    1.88
     years
    1.66
     Verhandlungen
    1.26
     period
    1.26
    ETIES
    1.25
    訁
    1.25
    Nguyễn
    1.19
     year
    1.18
     its
    1.17
    可能な
    1.16
    Activations Density 0.146%

    No Known Activations