© 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. 111139
    Prev
    Next
    INDEX
    Explanations

    mathematical or code contexts

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

    HTML/code formatting tags and mathematical notation symbols, particularly angle brackets and backslashes used in markup languages and LaTeX.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    </h5>
    -2.50
     After
    -2.13
    </h4>
    -2.08
     Perhaps
    -2.05
    </u>
    -2.00
     There
    -1.99
     Providing
    -1.95
     wahre
    -1.94
     Despite
    -1.94
    鉆
    -1.93
    POSITIVE LOGITS
    튿
    2.06
     efek
    1.99
     見える
    1.95
    螣
    1.93
    those
    1.88
     estratég
    1.80
    躂
    1.78
    瑢
    1.77
     chied
    1.76
     také
    1.73
    Activations Density 0.001%

    No Known Activations