© 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. 41-GEMMASCOPE-2-RES-262K
    7. 33488
    Prev
    Next
    INDEX
    Explanations

    took a phrase or clause

    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_all/layer_41_width_262k_l0_big
    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
     (_,
    0.45
     halen
    0.42
    ক্ষিপ্ত
    0.38
     anytime
    0.38
    olm
    0.38
    ActionResult
    0.38
    เสมอ
    0.37
    飜
    0.36
     aliqua
    0.36
     plej
    0.36
    POSITIVE LOGITS
     another
    0.44
    缶
    0.43
     poster
    0.39
     Poster
    0.39
     Situation
    0.38
     Tomato
    0.38
     Телефон
    0.38
    Tomato
    0.38
     Situ
    0.37
    ר
    0.37
    Activations Density 0.000%

    No Known Activations