© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57429
    Prev
    Next
    INDEX
    Explanations

    opera titles and characters

    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
     Vice
    -0.77
     maestra
    -0.75
    vington
    -0.73
     Oxford
    -0.73
     Bauern
    -0.72
     جان
    -0.71
     Rox
    -0.71
    ukkah
    -0.71
     ajustable
    -0.71
     coal
    -0.70
    POSITIVE LOGITS
     Siegfried
    0.82
    avier
    0.76
    Nib
    0.73
     gọi
    0.72
    平均
    0.71
     operas
    0.71
     встре
    0.71
     Alber
    0.70
     Tristan
    0.69
     يتيمه
    0.69
    Activations Density 0.009%

    No Known Activations