© 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. 40-GEMMASCOPE-2-RES-262K
    4. 570
    Prev
    Next
    INDEX
    Explanations

    re- continuations

    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_40_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
     pointillés
    0.39
    ilda
    0.38
    knie
    0.37
     Hausdorff
    0.36
     सीएचएसएल
    0.36
    は
    0.36
     Фонбет
    0.35
    胯
    0.35
    omio
    0.35
    ມີ
    0.35
    POSITIVE LOGITS
     re
    0.89
     Re
    0.85
    Re
    0.78
    re
    0.71
     ре
    0.70
     റെ
    0.62
     rej
    0.60
     reh
    0.57
     RE
    0.55
    becca
    0.55
    Activations Density 0.088%

    No Known Activations