© 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. 10-GEMMASCOPE-RES-131K
    7. 15512
    Prev
    Next
    INDEX
    Explanations

    suspected

    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_10/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
     about
    -2.50
     other
    -1.73
     the
    -1.70
    c
    -1.55
     because
    -1.55
    x
    -1.53
     more
    -1.52
     we
    -1.48
     many
    -1.47
    v
    -1.46
    POSITIVE LOGITS
     comprenant
    1.55
    красный
    1.52
     dizaines
    1.48
     ulter
    1.41
    羶
    1.40
     warmen
    1.39
     calendriers
    1.38
    ჻
    1.38
     principes
    1.38
     meilleures
    1.35
    Activations Density 0.130%

    No Known Activations