© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 29056
    Prev
    Next
    INDEX
    Explanations

    * and void

    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
     on
    -1.88
     to
    -1.75
    矬
    -1.47
    してます
    -1.41
     البته
    -1.34
     tendrá
    -1.34
     doesnt
    -1.28
     obtiene
    -1.28
     in
    -1.27
     encuentra
    -1.27
    POSITIVE LOGITS
    </strong>
    1.79
    }
    1.62
    {~
    1.50
    seguida
    1.40
     exemplaires
    1.40
     itſelf
    1.38
     italie
    1.36
     GEORG
    1.34
     saba
    1.32
    大
    1.32
    Activations Density 0.000%

    No Known Activations