© 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. 87084
    Prev
    Next
    INDEX
    Explanations

    vaccination, adolescents, costs, Raymond Dehn

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

    content related to health, medical information, and scientific research, particularly about vaccinations and disease prevention.

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

    The neuron fires strongly on tokens that appear in the title or headline lines of news‐style articles (e.g. the capitalized words and numbers at the start of an AP headline).

    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
    coefficient
    -0.80
    文書
    -0.78
    adak
    -0.77
    脑
    -0.73
    Hungry
    -0.73
    vita
    -0.71
    feng
    -0.71
    oceros
    -0.70
     Kein
    -0.70
     comprado
    -0.70
    POSITIVE LOGITS
     FDA
    1.01
     hesit
    0.93
     eligible
    0.91
     adolescent
    0.87
     confid
    0.86
     convin
    0.85
    高考
    0.82
    利率
    0.81
     Governor
    0.81
    Sleeve
    0.79
    Activations Density 0.003%

    No Known Activations