© 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. 1768
    Prev
    Next
    INDEX
    Explanations

    showing, dispensing, or presenting information

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

    The neuron strongly activates on C/C++ code identifiers containing “disp” or “isp” (e.g. macro or struct names like disp_404 or isp1760).

    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
     It
    -3.17
     employ
    -3.06
     był
    -2.88
     comunión
    -2.69
     adapt
    -2.52
    鈊
    -2.47
     exacting
    -2.42
     síntesis
    -2.41
     surpass
    -2.33
    几个月
    -2.31
    POSITIVE LOGITS
     uſed
    3.08
    他的
    2.61
    蚍
    2.48
    鱨
    2.44
    ates
    2.44
    <bos>
    2.39
     aussit
    2.39
    涐
    2.31
     faſt
    2.31
    滏
    2.30
    Activations Density 0.001%

    No Known Activations