© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73529
    Prev
    Next
    INDEX
    Explanations

    home insurance contents

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

    The neuron strongly activates on mentions of “renters insurance” and related policy‐coverage terms.

    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
    ческая
    -0.80
    meric
    -0.78
    ériale
    -0.77
    contextMenu
    -0.75
    торов
    -0.74
     PRISON
    -0.73
     starving
    -0.73
    ético
    -0.72
     Revenues
    -0.72
     tombs
    -0.72
    POSITIVE LOGITS
     replacement
    1.47
     homeowners
    1.44
     dwelling
    1.41
     homeowner
    1.30
     contents
    1.27
     home
    1.24
     rebuild
    1.23
     Replacement
    1.19
    dwelling
    1.18
     replacing
    1.13
    Activations Density 0.013%

    No Known Activations