© 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. 34-GEMMASCOPE-RES-131K
    4. 69846
    Prev
    Next
    INDEX
    Explanations

    health organizations and corporations

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

    South Asian names and terms, particularly those related to institutions, organizations, and places.

    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_34/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
     and
    -1.54
    おわりに
    -1.41
    》、《
    -1.25
    さんに
    -1.24
    ślę
    -1.23
     wanted
    -1.21
    あぁ
    -1.19
    嗚
    -1.15
    えっ
    -1.15
    あー
    -1.14
    POSITIVE LOGITS
    がありますが
    1.28
     другого
    1.20
    since
    1.13
     '',
    
    1.13
    などが
    1.13
    ということです
    1.12
     другой
    1.11
    かもしれませんが
    1.11
    見えます
    1.09
     Bakter
    1.08
    Activations Density 0.446%

    No Known Activations