© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109254
    Prev
    Next
    INDEX
    Explanations

    code definitions

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

    The neuron strongly activates on definition‐introducing keywords (especially "def" or “\def”) marking the start of a definition or macro.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     directives
    -0.85
    ❴
    -0.77
    HZ
    -0.77
     disinformation
    -0.77
    nowned
    -0.76
    んこ
    -0.75
    голов
    -0.75
    ОР
    -0.74
    heets
    -0.73
     obcí
    -0.73
    POSITIVE LOGITS
    射
    0.79
    ҙ
    0.79
     naira
    0.78
     Taft
    0.77
     backs
    0.76
     realtor
    0.76
     tratt
    0.74
    box
    0.73
     vieta
    0.73
     Corral
    0.73
    Activations Density 0.004%

    No Known Activations