© 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. 62672
    Prev
    Next
    INDEX
    Explanations

    data storage, abandonment cost, date, math

    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
     ICollection
    -0.90
     גבוה
    -0.81
     modernized
    -0.78
    糕
    -0.77
     ट्र
    -0.75
     hierbei
    -0.73
     według
    -0.73
     covert
    -0.73
     assassinated
    -0.73
     Africans
    -0.72
    POSITIVE LOGITS
     espagne
    0.88
    ?»
    0.84
     bandou
    0.83
    mester
    0.82
     Völker
    0.82
     pö
    0.82
    Rights
    0.80
     Toujours
    0.80
     Pense
    0.80
    Reached
    0.79
    Activations Density 0.000%

    No Known Activations