© 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. 20678
    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
     When
    -1.46
     abhor
    -1.39
     ziyaretçi
    -1.34
     olabilir
    -1.27
     erroneously
    -1.26
     deliciosa
    -1.26
     unusually
    -1.24
     razem
    -1.24
    gradation
    -1.22
     hinder
    -1.22
    POSITIVE LOGITS
    </strong>
    1.59
    ᯾
    1.25
     evolución
    1.24
    ']],
    1.22
    ”,
    1.20
    </th>
    1.20
    (),
    1.20
    ";
    1.20
    ",
    1.16
     نمی
    1.16
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.