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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40303
    Prev
    Next
    INDEX
    Explanations

    athletic performance**Rationale**:- `MAX_ACTIVATING_TOKENS` contains `increased`.- `TOKENS_AFTER_MAX_ACTIVATING_TOKEN` contains `athletic` and `helps` following `increased` potentially.The combination `increased athletic helps` strongly suggests a connection to athletic performance.The length is 2 words, which is between 3 and 20.It is a specific phrase and not a general concept like "positive outcomes".It avoids forbidden phrases

    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
     indi
    0.41
    ゔ
    0.41
     AVAILABLE
    0.41
    อร์ต
    0.40
     Nursery
    0.40
    的设计
    0.40
     CDN
    0.40
     affordability
    0.39
     disponibili
    0.39
     Hello
    0.39
    POSITIVE LOGITS
    ドラマ
    0.40
     перший
    0.39
    謀
    0.39
    岡
    0.38
    arks
    0.38
    して
    0.38
     मामले
    0.38
    iggins
    0.38
    一共
    0.37
    擬
    0.37
    Activations Density 0.001%

    No Known Activations