© 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. 48165
    Prev
    Next
    INDEX
    Explanations

    times and dates

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

    The neuron activates on numeric tokens—digits or multi‐digit numbers (e.g., dates, times, quantities).

    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
     UIT
    -1.24
    ICATION
    -1.20
     Mexicana
    -1.13
    ULAR
    -1.13
    时间的
    -1.12
    ি
    -1.11
    SIL
    -1.09
    饜
    -1.09
    导演
    -1.08
    kande
    -1.08
    POSITIVE LOGITS
    鉿
    1.24
     \
    1.18
     without
    1.17
    ă
    1.13
     folgte
    1.13
    睜
    1.12
     So
    1.12
     but
    1.10
     parfois
    1.10
     осіб
    1.09
    Activations Density 0.077%

    No Known Activations