© 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. 22-GEMMASCOPE-RES-131K
    7. 39076
    Prev
    Next
    INDEX
    Explanations

    Hindu deities

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

    The neuron detects mentions of Hindu deities (proper names of gods and their incarnations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     freaking
    -2.23
    こんなに
    -1.86
    元々
    -1.80
    の方も
    -1.76
    されていない
    -1.72
     nous
    -1.70
     drenched
    -1.66
    5
    -1.64
    0
    -1.64
     engrossed
    -1.64
    POSITIVE LOGITS
     искать
    1.80
     bílé
    1.70
        
    1.60
    {
    1.60
     vierte
    1.54
    ilustração
    1.53
    ————————————
    1.49
    ahh
    1.49
    (");
    1.48
    *',
    1.48
    Activations Density 0.006%

    No Known Activations