© 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. 91349
    Prev
    Next
    INDEX
    Explanations

    film, railroad, realm

    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
    비
    -0.74
    Ó
    -0.73
    teks
    -0.70
    염
    -0.70
     Amb
    -0.69
     teks
    -0.69
    原始内容存档
    -0.67
    óg
    -0.67
    моро
    -0.67
     अप
    -0.66
    POSITIVE LOGITS
     Rim
    0.89
    atamente
    0.88
    鎳
    0.82
    Rim
    0.78
    ătoare
    0.78
     Tempest
    0.77
     foothold
    0.75
    keteers
    0.75
    atiz
    0.73
     slat
    0.73
    Activations Density 0.009%

    No Known Activations