© 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. 15385
    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
     also
    -1.03
    .
    -1.02
     the
    -1.00
     another
    -0.98
     how
    -0.98
     every
    -0.97
     only
    -0.96
     similarly
    -0.96
     added
    -0.95
     sure
    -0.94
    POSITIVE LOGITS
    ৄ
    1.45
    偸
    1.23
     unseren
    1.09
    讫
    1.08
     AFFAIRS
    1.07
    together
    1.06
     nosotros
    1.06
    ৢ
    1.04
    ICAGO
    1.03
     TECHNIQUES
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.