© 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. 65470
    Prev
    Next
    INDEX
    Explanations

    temptation and succumbing to desires

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

    The neuron flags occurrences of the root “tempt” (in forms like tempted, tempting, tempt).

    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
    <tr>
    -0.84
    꿉
    -0.83
    Harvest
    -0.80
     खरीदा
    -0.80
    ographies
    -0.77
    Ram
    -0.77
    ignants
    -0.76
    Docker
    -0.76
    вики
    -0.76
    ʖ
    -0.73
    POSITIVE LOGITS
     temptation
    2.06
     temptations
    1.91
     Temptation
    1.53
     tempted
    1.50
    tempt
    1.24
     tempting
    1.18
     Satan
    1.16
     testing
    1.14
     Tempt
    1.13
     test
    1.10
    Activations Density 0.005%

    No Known Activations