© 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. 90512
    Prev
    Next
    INDEX
    Explanations

    ritualistic behaviours

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

    The neuron activates on words referring to formal ceremonies or prescribed procedures (e.g. “ritual,” “ritualistic,” “ceremonial,” “protocol”).

    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
     \
    -0.93
    返信
    -0.93
     genellikle
    -0.90
     spezi
    -0.90
    ेन
    -0.87
     abger
    -0.85
    幾乎
    -0.84
     각
    -0.83
     cull
    -0.83
    PROPERTIES
    -0.82
    POSITIVE LOGITS
    istic
    1.68
    istically
    1.43
    ISTIC
    1.29
    mistic
    1.09
     performed
    1.03
    躁
    1.01
     occasions
    0.98
     involving
    0.97
     participant
    0.96
     pratic
    0.94
    Activations Density 0.009%

    No Known Activations