© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    s
    -2.50
     of
    -1.94
     on
    -1.88
     своему
    -1.63
     his
    -1.63
    でも
    -1.62
    <strong>
    -1.57
     ‘
    -1.57
    x
    -1.55
    ”
    -1.53
    POSITIVE LOGITS
     diseñadores
    2.08
     révélé
    1.71
     primeiros
    1.70
     poderosa
    1.64
    ଽ
    1.62
    leis
    1.61
    ‪.‬‬
    1.60
     shrinking
    1.59
     soñar
    1.58
    让她
    1.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.