© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6804
    Prev
    Next
    INDEX
    Explanations

    crime, illegal, immoral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yz
    0.86
    edi
    0.85
     поэтому
    0.82
    otheli
    0.82
    ﺐ
    0.81
     Поэтому
    0.80
     escrita
    0.80
    ﻪ
    0.79
    ν
    0.78
     eleições
    0.78
    POSITIVE LOGITS
     मचा
    0.69
     مي‌
    0.65
    اہر
    0.64
    িন
    0.63
    FindAction
    0.63
    اي
    0.63
    ăm
    0.62
    ين
    0.61
     steril
    0.61
     congratulated
    0.61
    Activations Density 0.004%

    No Known Activations