© 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. 9861
    Prev
    Next
    INDEX
    Explanations

    Klein (name/place)

    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
    ↵↵
    -3.86
    瑨
    -3.13
    
    -3.08
    Ꮉ
    -3.06
    瞜
    -2.98
    焄
    -2.89
    )$.
    -2.84
     使っ
    -2.64
    ᨆ
    -2.48
    廰
    -2.47
    POSITIVE LOGITS
    橚
    3.28
    蟶
    2.81
     refugiados
    2.77
    ጢ
    2.63
    蠖
    2.55
    釭
    2.52
    葙
    2.50
    袛
    2.50
     étrangers
    2.48
    したり
    2.45
    Activations Density 0.002%

    No Known Activations