© 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. 57407
    Prev
    Next
    INDEX
    Explanations

    times century history study

    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
     to
    -2.13
    ↵
    -1.77
    __);
    -1.73
    ]}{
    -1.73
     in
    -1.66
     not
    -1.56
     just
    -1.52
     pertama
    -1.51
     although
    -1.49
     a
    -1.48
    POSITIVE LOGITS
     it
    3.05
     there
    2.66
     you
    2.45
     we
    2.02
    ,
    1.98
     manifiesto
    1.81
    Keterangan
    1.63
     vacacionales
    1.62
     alrededores
    1.61
     هناك
    1.59
    Activations Density 0.490%

    No Known Activations