© 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. 12972
    Prev
    Next
    INDEX
    Explanations

    redistribution and licensing

    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
     लेकिन
    -2.91
     But
    -2.69
    to
    -2.61
    x
    -2.45
    ↵↵
    -2.45
    j
    -2.44
    n
    -2.44
    la
    -2.38
    co
    -2.38
               
    -2.27
    POSITIVE LOGITS
     онъ
    2.50
     zelve
    2.34
     nowa
    2.28
     leef
    2.27
     oock
    2.17
    Stap
    2.16
     reservado
    2.16
    dengan
    2.16
    Fourni
    2.11
    França
    2.09
    Activations Density 0.030%

    No Known Activations