© 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. 14322
    Prev
    Next
    INDEX
    Explanations

    residency program

    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
     الجلد
    -1.87
     گیاه
    -1.72
    𝗼
    -1.71
    Šalt
    -1.58
     сахара
    -1.52
     religieux
    -1.50
     sés
    -1.49
    ׇ
    -1.47
     chrétienne
    -1.42
     Speisen
    -1.41
    POSITIVE LOGITS
    🪛
    2.48
    ּוֹ
    2.39
    ִּ
    1.91
    ַּ
    1.89
    ְּ
    1.87
    ύ
    1.77
    וּ
    1.75
     épo
    1.69
    ᾿
    1.66
    ֶּ
    1.65
    Activations Density 0.218%

    No Known Activations