© 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. 22-GEMMASCOPE-RES-131K
    7. 75290
    Prev
    Next
    INDEX
    Explanations

    religious conversion

    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_22/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
    -1.11
    F
    -1.05
    create
    -1.03
    p
    -1.03
     tervez
    -1.02
    知らせ
    -0.97
    last
    -0.96
    vang
    -0.96
     it
    -0.96
    hā
    -0.96
    POSITIVE LOGITS
     conversion
    1.51
     conversions
    1.30
     converted
    1.28
    cepted
    1.19
    鹋
    1.15
    ">!
    1.13
    conversion
    1.11
     joining
    1.10
    ilarities
    1.10
    принима
    1.07
    Activations Density 0.025%

    No Known Activations