© 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. 49865
    Prev
    Next
    INDEX
    Explanations

    drug use, pregnancy, death

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

    statistics about mortality, death rates, and demographic health data.

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

    The neuron focuses on spotting numeric and statistical expressions—especially rate, count, and increase figures—in demographic or health‐related data.

    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
     Survivors
    -0.79
     عروس
    -0.77
    幽默
    -0.77
    survi
    -0.75
    変換
    -0.74
     кер
    -0.73
     multilingual
    -0.73
     survivor
    -0.73
    ttu
    -0.73
     survivors
    -0.72
    POSITIVE LOGITS
    latest
    0.85
    drug
    0.84
    Drug
    0.83
     drug
    0.81
     Drug
    0.79
     useStyles
    0.79
     involving
    0.78
     fiore
    0.78
    middle
    0.77
    ftar
    0.76
    Activations Density 0.069%

    No Known Activations