© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 52517
    Prev
    Next
    INDEX
    Explanations

    declares rebellion

    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
    રૂ
    0.42
    大多數
    0.42
    機構
    0.42
     preclude
    0.40
    /
    0.40
     நிகழ்
    0.40
    \
    0.38
    投与
    0.37
    勞
    0.37
    行為
    0.36
    POSITIVE LOGITS
     आह्वान
    0.50
     berjudul
    0.47
     commandment
    0.47
     declaring
    0.47
     exhort
    0.45
     ingredient
    0.44
     encouraging
    0.44
     emoji
    0.43
     declares
    0.43
     aján
    0.43
    Activations Density 0.006%

    No Known Activations