© 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. 93825
    Prev
    Next
    INDEX
    Explanations

    software, products, and entities

    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
     सेकेंडरी
    0.44
    㺪
    0.43
    这部
    0.43
    主持人
    0.42
     πάντα
    0.41
     Yah
    0.41
    ниях
    0.41
    ப்பட்டது
    0.41
    囫
    0.41
    碩
    0.40
    POSITIVE LOGITS
     offered
    0.47
     religions
    0.46
     wearables
    0.45
     correlating
    0.44
    MappingURL
    0.44
    ットフォーム
    0.44
     folks
    0.43
     foods
    0.43
     you
    0.42
     facial
    0.42
    Activations Density 0.003%

    No Known Activations