© 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. 31-GEMMASCOPE-2-RES-262K
    7. 19131
    Prev
    Next
    INDEX
    Explanations

    code structure delimiters

    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
    会
    0.40
    则
    0.39
    ِل
    0.39
    后
    0.39
     then
    0.38
    प्पू
    0.37
     return
    0.37
     happ
    0.37
     então
    0.37
    ু
    0.36
    POSITIVE LOGITS
    arsipkan
    0.38
    י
    0.37
     எழுதிய
    0.36
     ограничи
    0.36
    ૩
    0.36
    リビング
    0.36
     রাখিয়া
    0.36
     নির্বাচন
    0.35
     Turnier
    0.35
     வகையான
    0.35
    Activations Density 0.018%

    No Known Activations