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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19977
    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
    this
    -2.13
     để
    -2.06
     visant
    -2.03
    ஂ
    -2.02
    0
    -1.95
     étranger
    -1.91
     officiels
    -1.86
     gestartet
    -1.83
    .=
    -1.81
    d
    -1.80
    POSITIVE LOGITS
     and
    2.53
     from
    1.90
     in
    1.86
     him
    1.83
     but
    1.69
     And
    1.61
     at
    1.59
    mpagne
    1.58
    itated
    1.57
     AND
    1.56
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.