© 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. 3477
    Prev
    Next
    INDEX
    Explanations

    misevaluated, motorengine

    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
    /
    -0.89
     just
    -0.85
    autonomie
    -0.82
    -
    -0.80
     деревьев
    -0.76
     Following
    -0.76
     viernes
    -0.75
    aéroport
    -0.74
     Making
    -0.74
    appré
    -0.74
    POSITIVE LOGITS
     embeddings
    1.02
     embroidery
    1.01
     Evolutionary
    0.99
     Ilustra
    0.98
     golfe
    0.98
     boîtier
    0.96
    гия
    0.94
     jų
    0.94
     Ethn
    0.93
     شوید
    0.91
    Activations Density 0.097%

    No Known Activations