© 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. 34-GEMMASCOPE-RES-131K
    7. 49939
    Prev
    Next
    INDEX
    Explanations

    out of

    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_34/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
    Struktur
    -0.73
     Código
    -0.72
     ナビ
    -0.68
     kei
    -0.68
     major
    -0.68
    Gü
    -0.67
     Aal
    -0.67
     fels
    -0.66
    лица
    -0.65
     inni
    -0.65
    POSITIVE LOGITS
    igkeit
    0.90
    rane
    0.89
     doors
    0.88
    concel
    0.87
    cheduling
    0.86
     procedimento
    0.82
    lared
    0.82
    uki
    0.82
     OUT
    0.82
     状
    0.81
    Activations Density 0.023%

    No Known Activations