© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73625
    Prev
    Next
    INDEX
    Explanations

    ente

    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
    ing
    -3.02
    ).
    -3.00
     Obtaining
    -2.88
    =
    -2.86
    2
    -2.81
     Virtually
    -2.80
     Emphas
    -2.72
     Acknowled
    -2.70
     Earlier
    -2.64
    In
    -2.63
    POSITIVE LOGITS
    豋
    2.84
    縂
    2.80
    彀
    2.75
    ſſi
    2.75
     火鍋
    2.50
    Ꮨ
    2.48
    ente
    2.45
     Portugu
    2.42
    焄
    2.41
    镝
    2.36
    Activations Density 0.020%

    No Known Activations