© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123734
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and phenomena

    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
    म्म
    0.49
     Nxc
    0.47
     Și
    0.47
    ك
    0.45
     fáciles
    0.44
     Starts
    0.43
     Startup
    0.43
    ম্ভীর
    0.43
    ว่าเป็น
    0.43
     ¿
    0.43
    POSITIVE LOGITS
    sts
    0.44
    战争
    0.43
    rma
    0.43
    凤凰
    0.42
    whereas
    0.42
     রোহিঙ্গ
    0.41
     സ്ത്ര
    0.41
    车
    0.41
     સફેદ
    0.40
    ເຮ
    0.39
    Activations Density 0.004%

    No Known Activations