© 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. 11215
    Prev
    Next
    INDEX
    Explanations

    any or must

    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
    MethodImpl
    -1.39
     الشاشة
    -1.34
     pomysł
    -1.32
    Algemeen
    -1.31
     alemanes
    -1.30
     essencial
    -1.28
    apparently
    -1.24
    Otros
    -1.23
     españoles
    -1.22
    commitment
    -1.22
    POSITIVE LOGITS
     that
    1.91
     new
    1.86
     his
    1.74
     this
    1.66
     future
    1.52
     zukünf
    1.41
    新
    1.38
     solution
    1.34
    new
    1.33
    他
    1.25
    Activations Density 0.050%

    No Known Activations