© 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. 66554
    Prev
    Next
    INDEX
    Explanations

    protective patterns and relationships

    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
     effectuer
    -1.33
     amsterdam
    -1.33
     braun
    -1.29
     uruguay
    -1.28
     feveral
    -1.27
    撵
    -1.27
     грамм
    -1.25
     firft
    -1.23
     sonde
    -1.23
    綺麗に
    -1.22
    POSITIVE LOGITS
     three
    1.65
     five
    1.48
     tiras
    1.45
     or
    1.44
     Američ
    1.41
    🪳
    1.39
     pictures
    1.39
     deliciosa
    1.38
    jadwal
    1.37
     two
    1.36
    Activations Density 0.055%

    No Known Activations