© 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. 106426
    Prev
    Next
    INDEX
    Explanations

    Leonardo DiCaprio and Leonardo da Vinci

    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
    RICT
    -0.79
     loob
    -0.76
     upang
    -0.73
    litre
    -0.73
    神器
    -0.72
     payers
    -0.71
     kneel
    -0.71
    FAMIL
    -0.71
     Sartre
    -0.70
     Mythology
    -0.70
    POSITIVE LOGITS
     Leonardo
    1.27
     Vinci
    1.11
     Mona
    1.04
    Leonardo
    1.01
    Vit
    0.98
     DiCaprio
    0.95
    Vinci
    0.90
    Mona
    0.89
     Vit
    0.88
     Codex
    0.84
    Activations Density 0.010%

    No Known Activations