© 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. 14978
    Prev
    Next
    INDEX
    Explanations

    @ mentions and decorators

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    </td>
    -2.50
    );
    -2.45
     (
    -2.11
     If
    -2.09
     protože
    -1.92
    しかし
    -1.91
     замена
    -1.88
     Betracht
    -1.87
    是被
    -1.81
    ↑↑↑</
    -1.80
    POSITIVE LOGITS
    {
    2.94
    z
    2.39
     gratuit
    2.38
    鵙
    2.16
    坶
    2.09
     amus
    2.08
     incred
    2.08
     constitue
    2.05
     véhicule
    2.02
     hotly
    2.00
    Activations Density 0.057%

    No Known Activations