© 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. 10-GEMMASCOPE-RES-131K
    7. 71020
    Prev
    Next
    INDEX
    Explanations

    real-time clock (RTC)

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

    The neuron fires on occurrences of the substring “rtc” (i.e. mentions of the real-time clock abbreviation RTC).

    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
    驁
    -2.64
    ⚋
    -2.63
    鲮
    -2.31
    蔟
    -2.30
    襴
    -2.30
    鹩
    -2.23
    </em>
    -2.22
    骜
    -2.20
     groter
    -2.20
    俅
    -2.13
    POSITIVE LOGITS
    {
    3.30
    to
    2.88
    \
    2.48
    t
    2.33
    ll
    2.31
    ar
    2.27
    AS
    2.11
    所有人都
    2.09
     dvou
    2.08
    n
    2.08
    Activations Density 0.003%

    No Known Activations