© 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. 111838
    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
    scor
    -0.97
    Materiál
    -0.93
     juegan
    -0.91
     forskellige
    -0.91
    admins
    -0.88
     geniales
    -0.88
    喟
    -0.87
    inderella
    -0.86
     Während
    -0.84
    lawesi
    -0.84
    POSITIVE LOGITS
     эффект
    1.00
     acamp
    0.99
     Neglect
    0.99
    vanju
    0.98
     roommate
    0.97
     aplic
    0.97
    ону
    0.96
     stroked
    0.96
    窕
    0.95
     fama
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.