© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 93703
    Prev
    Next
    INDEX
    Explanations

    code comments and technical terms

    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
    جيل
    0.43
    ᱗
    0.42
     kompleks
    0.42
    үнд
    0.42
    ହି
    0.41
     yaklaşık
    0.41
     ஆராய்ச்சி
    0.41
     комплекса
    0.40
     complex
    0.39
     tota
    0.39
    POSITIVE LOGITS
     detention
    0.46
     disobedience
    0.46
     प्रतिदिन
    0.46
     Wraith
    0.46
    ष्मान
    0.46
    ➡️
    0.45
     池
    0.45
    ot
    0.43
    อบ
    0.43
    बित
    0.43
    Activations Density 0.007%

    No Known Activations