© 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. 5576
    Prev
    Next
    INDEX
    Explanations

    our or us in multiple languages

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

    The neuron fires on strongly evaluative or emphatic words that convey criticism or moral judgment in formal statements.

    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
     taches
    0.57
     ().
    0.52
    /(
    0.51
     (\"
    0.51
    )(
    0.51
    ఱ
    0.50
     )(
    0.50
     $(
    0.49
     („
    0.49
     copyspace
    0.48
    POSITIVE LOGITS
    我们的
    0.68
    我們的
    0.68
    在我们
    0.67
     אנחנו
    0.65
    ພວກເຮົາ
    0.63
    !”
    0.61
     [
    0.60
     हमारे
    0.60
     mūsų
    0.60
    我们
    0.59
    Activations Density 1.550%

    No Known Activations