© 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. 34-GEMMASCOPE-RES-131K
    7. 45363
    Prev
    Next
    INDEX
    Explanations

    decision analysis systems

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

    The neuron detects technical research method and analysis terms (e.g. decision analysis, probabilistic sensitivity, multi-attribute health utility).

    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
    Behaviors
    -0.75
    mistry
    -0.74
     statistical
    -0.73
    PointF
    -0.73
    tská
    -0.72
    研究
    -0.71
    kob
    -0.71
     nằm
    -0.69
    quía
    -0.69
     लो
    -0.69
    POSITIVE LOGITS
     wicked
    1.09
     decision
    1.02
     unstructured
    1.01
    Wicked
    1.01
    DECISION
    0.97
    wicked
    0.96
     wickedness
    0.95
    decision
    0.91
     Decision
    0.91
    Decision
    0.89
    Activations Density 0.019%

    No Known Activations