© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 1873
    Prev
    Next
    INDEX
    Explanations

    gem mining history

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

    This neuron strongly responds to first-person narrative descriptions of the speaker’s or characters’ physical and emotional actions (e.g. smiled, nodded, took her hand, blushed).

    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
     (
    1.21
     
    1.15
     M
    1.05
    9
    1.05
    7
    1.05
    0
    1.02
     provides
    1.02
     $
    1.01
     "
    1.01
    5
    1.00
    POSITIVE LOGITS
     Jungkook
    1.45
     hắn
    1.39
     возле
    1.39
     Taehyung
    1.37
     pensamientos
    1.30
     слегка
    1.30
     минуту
    1.29
     trasero
    1.25
     えっと
    1.22
    嘴角
    1.21
    Activations Density 0.202%

    No Known Activations