Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 12282
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    ེ
    0.39
    ᅵ
    0.39
    ூன்
    0.39
     этому
    0.39
    литься
    0.38
    ফটেন্যান্ট
    0.37
    lığını
    0.36
    investissement
    0.35
    ጸ
    0.34
    ೀರ್
    0.34
    POSITIVE LOGITS
     These
    0.53
     এছাড়া
    0.52
    อื่นๆ
    0.52
    其他
    0.50
     altri
    0.49
     এছাড়াও
    0.49
    other
    0.49
     Additionally
    0.48
     Ngoài
    0.48
     D
    0.47
    Activations Density 0.294%

    No Known Activations