© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51246
    Prev
    Next
    INDEX
    Explanations

    German gravitational interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    ispiel
    0.47
    ంటున్నారు
    0.47
     ટો
    0.45
    ieve
    0.44
    ቂያ
    0.44
    漀
    0.43
    嬛
    0.41
    Only
    0.41
    อยู่ใน
    0.40
    డిన
    0.40
    POSITIVE LOGITS
     bút
    0.46
     mú
    0.46
     anu
    0.46
     cheese
    0.45
    راک
    0.45
     Adri
    0.44
     autón
    0.43
    Christmas
    0.43
    ਖ
    0.43
     marqu
    0.42
    Activations Density 0.003%

    No Known Activations