© 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. 91333
    Prev
    Next
    INDEX
    Explanations

    Children, killer dolls, toys

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

    The neuron fires on list‐style enumerations—sequences of items, names, or numbers separated by commas.

    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
     Advancement
    -0.80
     pillars
    -0.76
     furnishes
    -0.76
     Crum
    -0.76
     Flin
    -0.73
    erokee
    -0.72
    คว
    -0.72
     mucosal
    -0.71
     diversified
    -0.69
     leaves
    -0.69
    POSITIVE LOGITS
     doll
    1.16
    Child
    1.07
     Ch
    1.07
     Child
    0.98
     killer
    0.97
    Toy
    0.95
     CHILD
    0.93
     Numerade
    0.91
    Killer
    0.91
    Ch
    0.89
    Activations Density 0.016%

    No Known Activations