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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8991
    Prev
    Next
    INDEX
    Explanations

    view class, Age as, Growth factors

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

    XML/HTML code elements, particularly focusing on view tags and UI components.

    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
    Bises
    -1.48
    らせて
    -1.46
     tudom
    -1.33
    jąc
    -1.27
     blessure
    -1.26
    DANIEL
    -1.25
    Bisous
    -1.24
    蔓延
    -1.23
    циям
    -1.21
     remaster
    -1.20
    POSITIVE LOGITS
    </strong>
    1.66
    </code>
    1.55
    </u>
    1.50
              
    1.48
    但这
    1.46
    </i>
    1.34
     детьми
    1.33
     svært
    1.33
    </h3>
    1.32
    Addressing
    1.31
    Activations Density 0.010%

    No Known Activations