© 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. 93135
    Prev
    Next
    INDEX
    Explanations

    proper nouns and their continuations

    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
     '').
    -0.94
    Mejor
    -0.78
     dars
    -0.75
     cuddly
    -0.75
    ritsar
    -0.75
     getData
    -0.73
     varia
    -0.73
    udert
    -0.73
    ％
    -0.72
    Archiv
    -0.71
    POSITIVE LOGITS
    engines
    0.98
     engines
    0.93
    umbag
    0.79
     Engines
    0.78
     Comes
    0.77
     engine
    0.77
     volledig
    0.77
    pth
    0.76
    最早
    0.75
    ILayout
    0.75
    Activations Density 0.005%

    No Known Activations