© 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. 16-GEMMASCOPE-2-RES-262K
    7. 17591
    Prev
    Next
    INDEX
    Explanations

    legal, economic, historical, physical, administrative contexts

    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_16_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
    تها
    0.38
    то
    0.30
    т
    0.29
    ت
    0.29
    dır
    0.27
    تان
    0.27
     seiner
    0.27
    تهم
    0.26
    п
    0.26
    they
    0.26
    POSITIVE LOGITS
     límites
    0.28
    kari
    0.25
    ความ
    0.24
     dormancy
    0.24
    ون
    0.23
     rapids
    0.22
     exhaustion
    0.22
    蕖
    0.22
     riots
    0.21
     estuaries
    0.21
    Activations Density 0.055%

    No Known Activations