© 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. 39643
    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
    Sedan
    -1.06
    ⦑
    -1.04
    Cerca
    -0.99
    簠
    -0.98
    ()]);
    -0.98
    わかります
    -0.98
    >().
    -0.96
    ]]);
    -0.96
    )]);
    -0.94
    ごま
    -0.92
    POSITIVE LOGITS
     Israeli
    1.08
    町の
    0.96
     enticing
    0.94
     Intelligent
    0.91
     securities
    0.90
     intelligent
    0.90
     inference
    0.90
     Брази
    0.89
     tutto
    0.89
     noen
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.