© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79460
    Prev
    Next
    INDEX
    Explanations

    ages and durations

    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
    Negative Logits
    摟
    -1.05
     dormitorios
    -1.02
     courte
    -0.94
     veľ
    -0.94
    就不会
    -0.92
    鸩
    -0.91
    hezza
    -0.91
    rotto
    -0.90
     каждом
    -0.89
    揹
    -0.89
    POSITIVE LOGITS
     of
    1.55
     history
    1.24
     since
    1.19
     experience
    1.16
     as
    1.15
     existence
    1.05
     tradition
    1.00
     anniversary
    0.99
     ago
    0.98
     on
    0.88
    Activations Density 0.030%

    No Known Activations