© 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. 1889
    Prev
    Next
    INDEX
    Explanations

    effective strategy

    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
    シルバー
    -1.51
    —
    -1.45
     in
    -1.43
    好人
    -1.41
     my
    -1.34
     美しい
    -1.33
     normalerweise
    -1.33
     prachtige
    -1.31
    -
    -1.31
    コットン
    -1.30
    POSITIVE LOGITS
    ”:
    1.79
     climático
    1.62
     and
    1.56
    でしたか
    1.46
    
    1.45
    しました
    1.40
     adecuado
    1.39
     adecuada
    1.34
     используется
    1.32
    :”
    1.28
    Activations Density 0.027%

    No Known Activations