© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 111844
    Prev
    Next
    INDEX
    Explanations

    performance and safety descriptions

    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
     &/
    0.46
    及其
    0.44
    中有
    0.42
     および
    0.41
    이었다
    0.40
    VITY
    0.40
    이었
    0.39
    および
    0.39
    志
    0.37
     ਅਤੇ
    0.37
    POSITIVE LOGITS
    िस्थित
    0.48
     अभी
    0.46
     ആവശ്യമ
    0.46
    subtract
    0.45
     ब्लॉ
    0.45
    अभी
    0.45
     सेमीफाइनल
    0.44
    kaggle
    0.44
     लिंक
    0.43
    ர்ஸ்
    0.43
    Activations Density 0.006%

    No Known Activations