© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74559
    Prev
    Next
    INDEX
    Explanations

    natural gas industry and supply

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ↵
    -1.65
     Houſe
    -1.60
    Продам
    -1.53
     Inſ
    -1.51
    スポンサーリンク
    -1.41
     vermelhas
    -1.39
    加拿大
    -1.38
    也是
    -1.38
    verständ
    -1.34
     نداره
    -1.33
    POSITIVE LOGITS
     to
    1.58
    1.34
    1.33
     about
    1.30
     supports
    1.30
     via
    1.28
    1.26
    たつ
    1.25
    
    1.25
    ኧ
    1.21
    Activations Density 0.032%

    No Known Activations