© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42868
    Prev
    Next
    INDEX
    Explanations

    min/max operations

    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
     we
    -1.63
    听到了
    -1.48
     who
    -1.47
     cómodo
    -1.37
     możemy
    -1.36
    还是很
    -1.34
    都是在
    -1.33
     previamente
    -1.28
     nurturing
    -1.27
     provenientes
    -1.27
    POSITIVE LOGITS
    عالی
    1.63
    کیف
    1.48
     anivers
    1.46
     pantalon
    1.45
     ultimi
    1.44
    jednoc
    1.42
    گروه
    1.36
     galeria
    1.35
    mereka
    1.34
    Среди
    1.34
    Activations Density 0.012%

    No Known Activations