© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130801
    Prev
    Next
    INDEX
    Explanations

    controlled study, comparison, tyrosine, Q:

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

    HTML and CSS elements related to content layout and structure.

    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
     même
    -1.37
    ੨
    -1.22
     schaff
    -1.19
     lixo
    -1.16
     astuces
    -1.14
     vraiment
    -1.09
     akzep
    -1.07
     who
    -1.07
     pięk
    -1.06
     also
    -1.05
    POSITIVE LOGITS
    投稿日
    0.98
    Numerous
    0.96
     пун
    0.95
     fub
    0.93
    šas
    0.91
    とある
    0.91
    みなさん
    0.89
    不得不说
    0.89
    近年来
    0.89
    自从
    0.89
    Activations Density 0.003%

    No Known Activations