© 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. 22-GEMMASCOPE-RES-131K
    7. 12422
    Prev
    Next
    INDEX
    Explanations

    genome ANNOUNCEMENT, sequence

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

    scientific publication elements such as headers, annotations, and taxonomic names in academic papers.

    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_22/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
     any
    -1.11
     típico
    -1.09
     all
    -1.00
    鬱
    -0.99
     trajo
    -0.93
     Your
    -0.93
    购物
    -0.93
    皈
    -0.93
     suficientemente
    -0.92
     children
    -0.92
    POSITIVE LOGITS
     bija
    1.16
     parlando
    1.12
     Xa
    1.06
     venerdì
    1.05
    úť
    1.05
     htons
    1.04
    otriz
    1.04
     grp
    1.04
     gegenüber
    1.04
     yii
    1.03
    Activations Density 0.038%

    No Known Activations