© 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. 41426
    Prev
    Next
    INDEX
    Explanations

    heretofore devised

    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
    also
    -1.45
    Also
    -1.38
     also
    -1.37
    también
    -1.30
    のかもしれません
    -1.25
     también
    -1.18
     także
    -1.18
    幫忙
    -1.16
     one
    -1.16
    也會
    -1.14
    POSITIVE LOGITS
     varme
    1.62
     is
    1.54
     stadig
    1.47
     masih
    1.47
     síntesis
    1.39
     voks
    1.38
     forskellige
    1.38
     varmt
    1.37
     mulig
    1.36
    itação
    1.36
    Activations Density 0.072%

    No Known Activations