© 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. 22-GEMMASCOPE-RES-131K
    7. 129967
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     charla
    -0.99
    随意
    -0.93
    itzar
    -0.91
     finally
    -0.90
     permiti
    -0.89
    Fernsehserie
    -0.86
     Pueden
    -0.86
     kerana
    -0.86
     MonoBehaviour
    -0.85
    頂き
    -0.85
    POSITIVE LOGITS
     and
    1.33
     offiziell
    0.82
    細かい
    0.81
    Detalles
    0.81
     aéro
    0.79
     edilen
    0.77
     werken
    0.75
    ftant
    0.75
     defense
    0.74
    snowy
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.