© 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. 60316
    Prev
    Next
    INDEX
    Explanations

    side effects

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

    references to adverse side effects or toxicity of medications or treatments.

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

    This neuron fires on quantitative information—especially numbers, dosages, counts, and severity or frequency descriptors that convey measurable or statistical details.

    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
    getJSONObject
    -0.87
    mentable
    -0.84
     zug
    -0.83
     splashes
    -0.78
     можем
    -0.77
    strup
    -0.75
    cimentos
    -0.75
    liciter
    -0.74
    uchen
    -0.73
    獺
    -0.73
    POSITIVE LOGITS
     side
    5.22
    Side
    3.84
     Side
    3.77
     SIDE
    3.16
    side
    3.13
    SIDE
    2.78
    副作用
    2.75
     побо
    2.53
     adverse
    2.53
     Nebenwirkungen
    2.34
    Activations Density 0.165%

    No Known Activations