© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19022
    Prev
    Next
    INDEX
    Explanations

    N-linked structures and districts

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific or legal terms and phrases, particularly those related to specialized nomenclature.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⩩
    -1.84
     尔
    -1.83
    Веду
    -1.81
    ennung
    -1.79
    前は
    -1.77
    }
    -1.75
    UCIÓN
    -1.69
     scheinen
    -1.69
     ordinaires
    -1.68
     enormous
    -1.66
    POSITIVE LOGITS
    将会
    1.93
    方面的
    1.91
    selbe
    1.85
     tendrá
    1.84
    ).}
    1.79
    蔟
    1.77
    ՚
    1.72
    跸
    1.67
    鶫
    1.67
     serán
    1.66
    Activations Density 0.452%

    No Known Activations