© 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. 40638
    Prev
    Next
    INDEX
    Explanations

    real return and general intelligence

    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
     美
    0.48
     電
    0.47
     分
    0.46
     sluč
    0.46
     透明
    0.45
     isomers
    0.45
     別
    0.44
     Australien
    0.44
     denaturation
    0.43
     zdroj
    0.43
    POSITIVE LOGITS
    业务
    0.48
    ressive
    0.47
    逻
    0.47
    ных
    0.43
     रीजनिंग
    0.42
     критери
    0.41
     consegu
    0.40
    iz
    0.40
    任务
    0.40
    𝒊
    0.40
    Activations Density 0.002%

    No Known Activations