© 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. 27014
    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
     consists
    -0.97
     glaub
    -0.84
     majority
    -0.80
     their
    -0.79
     establishment
    -0.75
    rono
    -0.73
    tisan
    -0.73
     cryptographic
    -0.73
     akibat
    -0.72
     story
    -0.72
    POSITIVE LOGITS
    licopter
    1.09
    saying
    1.00
    ruptcy
    0.97
    我还是
    0.96
    still
    0.96
    Saying
    0.96
    ebly
    0.91
    taires
    0.89
     هفته
    0.89
    还是
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.