© 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. 15
    Prev
    Next
    INDEX
    Explanations

    java libraries and imports

    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
    thè
    -1.36
     provide
    -1.36
     this
    -1.36
    ----</
    -1.34
     apresentar
    -1.30
    tská
    -1.30
    RIED
    -1.30
     there
    -1.29
    Zeneca
    -1.29
     sicheren
    -1.28
    POSITIVE LOGITS
     soll
    1.69
     
    1.66
    t
    1.64
    u
    1.46
    me
    1.43
    ug
    1.41
    ig
    1.41
    on
    1.39
    w
    1.36
    l
    1.34
    Activations Density 0.010%

    No Known Activations