© 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. 15897
    Prev
    Next
    INDEX
    Explanations

    I'm sorry, apologize

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

    The neuron detects apology expressions—particularly occurrences of “sorry” (and related apology phrases).

    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
    Сейчас
    0.88
    이라
    0.84
     ನೋಡ
    0.82
    ぁ
    0.82
    やっと
    0.80
    이니까
    0.79
    कर्मा
    0.77
     месяца
    0.75
     рассказыва
    0.74
    𝙷
    0.74
    POSITIVE LOGITS
    vad
    0.85
    vaj
    0.79
     Offered
    0.79
    rieben
    0.78
    vl
    0.77
    vat
    0.75
    adati
    0.75
    󠁬
    0.75
     Moreover
    0.74
    iladi
    0.74
    Activations Density 0.012%

    No Known Activations