© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15984
    Prev
    Next
    INDEX
    Explanations

    Indonesia and Indonesian

    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_22/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
    </i>
    -1.79
    感じで
    -1.66
     meinem
    -1.52
    </h1>
    -1.49
    すっ
    -1.48
     respectivas
    -1.47
    ほうがいい
    -1.45
    ほら
    -1.45
    あぁ
    -1.45
    </b>
    -1.45
    POSITIVE LOGITS
     Indonesia
    1.59
    ONESIA
    1.59
    schild
    1.55
     Genehmigung
    1.53
     Bali
    1.49
    térature
    1.46
     Indonesian
    1.41
    脔
    1.41
    Indonesia
    1.38
    relate
    1.38
    Activations Density 0.023%

    No Known Activations