© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108111
    Prev
    Next
    INDEX
    Explanations

    confused or agitated states

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

    The neuron detects mentions of neurological dysfunction—especially terms around “encephalopathy” and related indicators of brain disorder or altered consciousness.

    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
    mson
    -0.76
    inflate
    -0.76
     colds
    -0.74
    嘮
    -0.71
     Preg
    -0.70
     centi
    -0.69
     মা
    -0.69
    ╔
    -0.67
    締め
    -0.67
    cipes
    -0.67
    POSITIVE LOGITS
     agitation
    2.03
     agitated
    1.55
     confusion
    1.41
    confusion
    1.30
     Confusion
    1.28
    Confusion
    1.25
     confused
    1.23
     delirium
    1.23
     restlessness
    1.18
     confuse
    1.05
    Activations Density 0.067%

    No Known Activations