© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14044
    Prev
    Next
    INDEX
    Explanations

    capable of sensing magic

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

    The neuron fires on grand or epic descriptors—words that emphasize great power, magic, or mighty forces.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0.94
    腼
    0.77
    屌
    0.76
    좇
    0.76
     classy
    0.75
     snappy
    0.75
    惦
    0.75
     everywhere
    0.72
    女朋友
    0.72
    睬
    0.72
    POSITIVE LOGITS
     teleport
    1.20
     criaturas
    0.99
     során
    0.95
     Geräte
    0.93
     otorg
    0.91
     humanoid
    0.91
     rune
    0.89
     magia
    0.89
     маги
    0.89
     energía
    0.88
    Activations Density 0.000%

    No Known Activations