© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133098
    Prev
    Next
    INDEX
    Explanations

    descriptive modifiers and list markers

    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
    ساعد
    0.34
    ۱۰
    0.33
     fato
    0.32
    ⁾
    0.32
    ணய
    0.32
    ۱۹
    0.32
    ಕಾಶ
    0.31
     Böyle
    0.31
    卽
    0.31
     futura
    0.31
    POSITIVE LOGITS
    ।
    0.35
    Navbar
    0.34
    ave
    0.33
     employees
    0.33
     криптовалю
    0.33
     estoppel
    0.32
     ?.
    0.32
     Pharmaceuticals
    0.31
     mathvariant
    0.31
    ។
    0.31
    Activations Density 0.002%

    No Known Activations