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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 16242
    Prev
    Next
    INDEX
    Explanations

    del

    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_31_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
    </footer>
    0.60
    ை
    0.57
    口气
    0.55
    चार्य
    0.53
     defendant
    0.52
    ONENTS
    0.52
    ം
    0.52
    }".
    0.52
    opaedia
    0.51
    ম্ব
    0.51
    POSITIVE LOGITS
     Del
    1.28
    Del
    1.23
    DEL
    1.17
     DEL
    1.11
    del
    1.04
     Deli
    0.97
     Dele
    0.94
     del
    0.89
     dele
    0.83
     Delaware
    0.82
    Activations Density 0.086%

    No Known Activations