© 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. 44410
    Prev
    Next
    INDEX
    Explanations

    conceals, restock, ado, undeliverable

    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>
    -3.09
    {
    -3.09
     vollständige
    -3.02
     letzte
    -2.98
    .
    -2.98
     offizielle
    -2.94
    in
    -2.94
    la
    -2.91
     größte
    -2.84
     zentrale
    -2.83
    POSITIVE LOGITS
    StoryboardSegue
    2.70
    ឵
    2.67
    
    2.61
     enfant
    2.59
     fantastique
    2.56
    違った
    2.56
    ViewChild
    2.53
    ครื่อง
    2.52
    ?"
    2.33
    
    2.33
    Activations Density 0.006%

    No Known Activations