© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4149
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     would
    -0.81
    ectoria
    -0.75
    вают
    -0.75
     algun
    -0.75
     tyme
    -0.74
    ป
    -0.73
    OrCreate
    -0.73
    стта
    -0.73
     foon
    -0.73
     کردم
    -0.72
    POSITIVE LOGITS
    忱
    0.88
    Utili
    0.86
     đặc
    0.85
    Extremely
    0.83
     MATTERS
    0.82
     complet
    0.79
    릎
    0.79
    Recon
    0.79
     juste
    0.78
     EVEN
    0.78
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.