© 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. 71179
    Prev
    Next
    INDEX
    Explanations

    gpio pins and code

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

    The neuron fires for references to GPIO- or pin-control header files or API calls (i.e. Linux GPIO/pinctrl code identifiers).

    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
     That
    -2.78
    </h5>
    -2.61
    l
    -2.58
     —
    -2.50
    ?
    -2.41
     Why
    -2.27
    </b>
    -2.27
     что
    -2.23
     is
    -2.17
    g
    -2.14
    POSITIVE LOGITS
     magnético
    2.73
     Ráp
    2.39
    眛
    2.36
     排骨
    2.33
     钢琴
    2.28
    เพื่อ
    2.27
     เปิด
    2.22
    ㈯
    2.19
    ᆞ
    2.19
     Fácil
    2.19
    Activations Density 0.001%

    No Known Activations