© 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. 1126
    Prev
    Next
    INDEX
    Explanations

    deeper dive into

    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
    与其
    -1.63
    𐐪
    -1.61
     relojes
    -1.60
     agujas
    -1.58
     macetas
    -1.55
     męskie
    -1.50
    erweise
    -1.50
     besonder
    -1.47
     tamaños
    -1.46
    hermosa
    -1.45
    POSITIVE LOGITS
     on
    2.00
    s
    1.94
    tım
    1.76
     into
    1.72
    ꦒ
    1.55
     through
    1.55
     使っ
    1.53
     upor
    1.45
    alties
    1.44
    rische
    1.43
    Activations Density 0.008%

    No Known Activations