© 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. 56029
    Prev
    Next
    INDEX
    Explanations

    questions or lists

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

    The neuron fires strongly on mentions of “water,” especially in the context of aquarium water‐changing or tank maintenance.

    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
    mRNA
    -0.91
    GFP
    -0.84
    \}^{
    -0.84
    ruptcy
    -0.79
    thè
    -0.79
    审查
    -0.78
    toplasm
    -0.78
    virano
    -0.78
     najlep
    -0.76
    卢
    -0.76
    POSITIVE LOGITS
     test
    1.02
     Readings
    1.00
     testing
    0.99
     tests
    0.98
     Nitrate
    0.97
     readings
    0.92
     nitrate
    0.92
     parameters
    0.90
    睾
    0.85
     weekly
    0.84
    Activations Density 0.010%

    No Known Activations