© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15297
    Prev
    Next
    INDEX
    Explanations

    not even

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

    The neuron strongly responds to concessive or emphasis adverbs—especially the word “even.”

    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
     mọi
    0.96
     oth
    0.95
     همه
    0.92
     refine
    0.91
    ましたが
    0.90
     QtWidgets
    0.89
     subplot
    0.89
    '
    0.87
     XI
    0.86
     inflict
    0.85
    POSITIVE LOGITS
     siquiera
    1.16
    LM
    1.05
    РЕ
    1.05
    handed
    1.04
    LS
    1.01
    LOGIN
    1.00
    Ls
    1.00
     গিয়েছিল
    1.00
    可以说是
    1.00
    िवे
    1.00
    Activations Density 0.045%

    No Known Activations