© 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. 41-GEMMASCOPE-2-RES-262K
    7. 5623
    Prev
    Next
    INDEX
    Explanations

    new followed by common code/data structures

    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_all/layer_41_width_262k_l0_big
    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
    <unused2175>
    0.57
    াত্মক
    0.55
    ারি
    0.55
    รรม
    0.54
    وٹی
    0.51
    ้ำ
    0.51
    ိုင်
    0.51
    ریق
    0.51
    ตาล
    0.50
    <unused973>
    0.50
    POSITIVE LOGITS
     HashMap
    0.66
    Еще
    0.55
     Guerra
    0.55
     Dés
    0.54
     StringBuilder
    0.53
     LinkedList
    0.52
     Nazi
    0.50
     Fiesta
    0.50
     HashSet
    0.49
     Delhi
    0.48
    Activations Density 0.002%

    No Known Activations