© 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. 98444
    Prev
    Next
    INDEX
    Explanations

    seizures

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

    terms and descriptions related to epileptic seizures and neurological conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on mentions of epilepsy and seizure‐related terms, effectively spotting when the text is discussing seizure disorders.

    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
    LineChart
    -0.96
     XXVI
    -0.91
     ballads
    -0.90
    函
    -0.88
    POSURE
    -0.85
     humanist
    -0.83
     ballad
    -0.83
     lavorare
    -0.82
     rami
    -0.81
     Quito
    -0.77
    POSITIVE LOGITS
     jerk
    0.89
     características
    0.85
    頑
    0.84
     žen
    0.83
     característica
    0.83
     abolished
    0.82
    ]+"
    0.82
     médicos
    0.81
     Schutz
    0.81
     mismas
    0.81
    Activations Density 0.203%

    No Known Activations