© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12850
    Prev
    Next
    INDEX
    Explanations

    rtc_time

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

    The neuron fires on code identifiers naming hardware interfaces or low‐level modules—e.g. header filenames or symbols like “i2c,” “rtc,” “pci,” “usb,” etc.

    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
     Those
    -1.48
     esos
    -1.48
     For
    -1.48
    cifix
    -1.45
     Verbrechen
    -1.41
     Thanks
    -1.41
     When
    -1.38
     Gefang
    -1.36
    ação
    -1.34
     others
    -1.34
    POSITIVE LOGITS
    EN
    1.58
    🤢
    1.56
    </i>
    1.55
    🤡
    1.48
    🧐
    1.48
    😰
    1.46
    😓
    1.46
    ✨✨
    1.45
    🤨
    1.45
    😱
    1.45
    Activations Density 0.025%

    No Known Activations