© 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. 3554
    Prev
    Next
    INDEX
    Explanations

    objects and containers

    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
     algorithms
    0.29
     scalability
    0.29
     लक्षात
    0.27
    ब
    0.27
     کاهش
    0.27
     ঘনত্ব
    0.27
     réduire
    0.27
    Evans
    0.27
    ௐ
    0.27
     textarea
    0.26
    POSITIVE LOGITS
     holder
    0.38
     held
    0.33
     tucked
    0.30
     belt
    0.30
     Holders
    0.29
     pouch
    0.29
    setOn
    0.29
    cheon
    0.29
     flung
    0.29
    ALLED
    0.29
    Activations Density 0.211%

    No Known Activations