© 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. 7101
    Prev
    Next
    INDEX
    Explanations

    not responsible for

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

    The neuron flags typical legal‐disclaimer language—phrases like “not responsible,” “reserve the right,” “assumes no liability,” and “shall not be liable” in terms-of-service or warranty text.

    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
    가
    0.60
    -
    0.55
     obtus
    0.55
    ના
    0.50
     belong
    0.48
    吼
    0.48
     defeat
    0.47
     belonged
    0.47
     defeating
    0.47
    COME
    0.47
    POSITIVE LOGITS
     কর্তৃক
    0.61
     Nurses
    0.60
     ответственность
    0.60
    读者
    0.60
     blames
    0.60
     serta
    0.57
    丝毫
    0.57
    ೃ
    0.57
     Publishers
    0.56
     نهایت
    0.55
    Activations Density 0.039%

    No Known Activations