© 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. 12545
    Prev
    Next
    INDEX
    Explanations

    scripting language

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

    The neuron fires on occurrences of the word “no,” detecting that specific negation token.

    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
    نز
    0.77
    ُن
    0.76
     semuanya
    0.68
    𝐤
    0.67
     ronde
    0.66
     cez
    0.66
     jantung
    0.66
    heard
    0.65
    ﯼ
    0.65
    ّى
    0.64
    POSITIVE LOGITS
     capitalizing
    0.77
     dmg
    0.74
     cabling
    0.72
     trova
    0.71
     불구하고
    0.69
     यदि
    0.67
     ЗА
    0.67
     বৃহত্তর
    0.67
     CIRCA
    0.66
     potuto
    0.66
    Activations Density 0.000%

    No Known Activations