© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113810
    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
     Ereignisse
    -1.13
     diriger
    -1.04
     Verantwort
    -0.99
     手順
    -0.99
    本当
    -0.96
     verantwort
    -0.95
    Never
    -0.93
     Nachbarn
    -0.93
     *
    -0.92
     Gläub
    -0.91
    POSITIVE LOGITS
     CGRectMake
    0.94
    なくなる
    0.93
     Normdatei
    0.89
    moy
    0.88
    podcast
    0.88
     descans
    0.87
     columna
    0.87
    ัตว์
    0.86
     constitucional
    0.86
     tons
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.