© 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. 40-GEMMASCOPE-2-RES-262K
    7. 191608
    Prev
    Next
    INDEX
    Explanations

    geographical features or locations

    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_40_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
    ’!
    0.47
     모든
    0.40
    ͑
    0.39
     крайне
    0.38
    imester
    0.37
    庀
    0.37
     germinate
    0.36
     commutes
    0.36
     abrang
    0.35
    乘
    0.35
    POSITIVE LOGITS
     charting
    0.38
     shores
    0.38
     historian
    0.37
     pinning
    0.37
    年代
    0.35
     Value
    0.35
    dish
    0.35
     pinned
    0.35
    磯
    0.35
     Insight
    0.35
    Activations Density 0.000%

    No Known Activations