© 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. 12736
    Prev
    Next
    INDEX
    Explanations

    database, get, graphics, prepare, inputs, randn, seed, read

    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
    If
    -1.88
    琑
    -1.72
    surate
    -1.72
    
    -1.68
    "../
    -1.66
    焢
    -1.66
    𐐪
    -1.59
     menurut
    -1.59
    How
    -1.56
    卨
    -1.51
    POSITIVE LOGITS
     is
    1.45
    mohon
    1.39
     something
    1.37
     about
    1.37
    湏
    1.34
    OfSize
    1.30
     calefacción
    1.30
    旒
    1.28
    OnEvent
    1.26
    ForValue
    1.25
    Activations Density 0.001%

    No Known Activations