© 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. 946
    Prev
    Next
    INDEX
    Explanations

    climate change emergency

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

    content related to climate change, environmental issues, and ecological concerns.

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

    The neuron strongly activates on longer, semantically rich content words (especially topic‐specific nouns and adjectives) rather than on common function words.

    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
     Obama
    -0.85
     окружа
    -0.84
     protocol
    -0.81
     варто
    -0.81
    奬
    -0.79
    ♻
    -0.79
    扰
    -0.79
    DVD
    -0.78
     DVD
    -0.78
     انرژی
    -0.77
    POSITIVE LOGITS
     emergency
    1.09
    Emergency
    0.99
    emergency
    0.93
     emergencia
    0.89
     EMERGENCY
    0.85
     현재
    0.84
    giers
    0.84
     Emergency
    0.83
    moth
    0.81
     garantire
    0.81
    Activations Density 0.016%

    No Known Activations