© 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. 102028
    Prev
    Next
    INDEX
    Explanations

    foreign languages and concepts

    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>
    -1.94
    >
    -1.64
    </u>
    -1.63
    ”
    -1.58
     this
    -1.58
    <h3>
    -1.55
     χρήση
    -1.55
     they
    -1.53
     there
    -1.53
    <bos>
    -1.52
    POSITIVE LOGITS
     Redacción
    1.88
    来て
    1.79
    偁
    1.77
    鸶
    1.77
     mân
    1.75
     filós
    1.70
     dát
    1.70
    Kemudian
    1.66
     cumbre
    1.65
    Selain
    1.63
    Activations Density 0.004%

    No Known Activations