© 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. 40066
    Prev
    Next
    INDEX
    Explanations

    IPC and IPCC acronyms

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

    The neuron detects occurrences of the acronym “IPC” (inter‐process communication) in technical passages.

    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
    ↵
    -3.22
    .
    -2.52
     —
    -2.45
    见状
    -2.38
     proponents
    -2.38
     così
    -2.33
    们的
    -2.17
     frü
    -2.14
    '
    -2.13
     elaborated
    -2.11
    POSITIVE LOGITS
    🌸
    2.78
    🌷
    2.53
    釭
    2.52
    💟
    2.44
    🌟
    2.42
    💓
    2.42
    💞
    2.41
    ㈮
    2.39
    🌺
    2.38
    ooooo
    2.36
    Activations Density 0.002%

    No Known Activations