© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73088
    Prev
    Next
    INDEX
    Explanations

    scientific research descriptions

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

    code syntax patterns in web development frameworks like Angular, React, and Vue, particularly focusing on component configuration properties.

    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
     gave
    -1.53
    </td>
    -1.51
    >
    -1.45
     $
    -1.45
    '
    -1.43
     you
    -1.42
    了不少
    -1.41
    @
    -1.37
    $
    -1.37
     gutem
    -1.34
    POSITIVE LOGITS
     prodotti
    1.58
    accessoires
    1.45
     dinero
    1.45
    嵛
    1.45
     škole
    1.43
    plakat
    1.42
    
    1.42
    垸
    1.40
    znak
    1.37
    .}(
    1.36
    Activations Density 0.003%

    No Known Activations