© 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. 110796
    Prev
    Next
    INDEX
    Explanations

    obstructive pulmonary disease

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

    German language words, including "unter", "obstructive", and German city names like "Montpellier".

    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
    T
    -2.63
     
    -2.59
    珰
    -2.58
    '
    -2.52
    Y
    -2.38
    its
    -2.25
     наша
    -2.22
    或者
    -2.20
     这个
    -2.19
     provocando
    -2.19
    POSITIVE LOGITS
    饜
    3.17
    ⎆
    3.16
    
    2.63
     птица
    2.47
    妧
    2.45
    ية
    2.42
     marvel
    2.38
    珦
    2.36
    綃
    2.36
     Weisheit
    2.34
    Activations Density 0.003%

    No Known Activations