© 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. 98547
    Prev
    Next
    INDEX
    Explanations

    scientific research and publications

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

    text discussing controversies and criticisms related to the pharmaceutical, supplement, and medical industries.

    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
     cristianos
    -1.34
    вѣ
    -1.32
    рѣ
    -1.30
     operasi
    -1.28
     крепления
    -1.27
     фаса
    -1.27
    ソフトウェア
    -1.27
     パソコン
    -1.26
     vectores
    -1.25
     заметил
    -1.25
    POSITIVE LOGITS
     research
    1.84
     published
    1.66
     scientific
    1.60
     studies
    1.54
     néer
    1.51
     dança
    1.44
     publications
    1.42
     actrice
    1.41
     десер
    1.40
     benzin
    1.38
    Activations Density 0.149%

    No Known Activations