© 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. 84842
    Prev
    Next
    INDEX
    Explanations

    president

    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
    ."
    -2.00
     ribuan
    -1.67
    !"
    -1.67
    就算是
    -1.64
    ,"
    -1.64
    …"
    -1.59
    。"
    -1.59
    肯定是
    -1.59
     Mereka
    -1.59
     où
    -1.59
    POSITIVE LOGITS
     comanda
    1.91
    糴
    1.80
     Praga
    1.47
     echi
    1.46
     Affaires
    1.45
     faca
    1.44
     stanga
    1.44
    鷙
    1.41
     vanden
    1.41
     殼
    1.40
    Activations Density 0.032%

    No Known Activations