© 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. 65358
    Prev
    Next
    INDEX
    Explanations

    gene suppression

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

    parenthetical citations in academic or reference text.

    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
     There
    -1.65
    </h3>
    -1.61
     ensuring
    -1.53
     where
    -1.48
    <strong>
    -1.46
     What
    -1.42
     so
    -1.41
     which
    -1.41
     As
    -1.41
     interestingly
    -1.41
    POSITIVE LOGITS
     viſ
    1.70
    commonly
    1.64
    
    1.57
     hogares
    1.54
    癔
    1.54
     heridos
    1.53
     INFORMACIÓN
    1.52
    肏
    1.48
    throughout
    1.47
    originally
    1.46
    Activations Density 0.033%

    No Known Activations