© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 257393
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ني
    0.44
    鑄
    0.43
     تحفظ
    0.42
    صب
    0.42
    فع
    0.41
    ورة
    0.41
    紅色
    0.41
    屬
    0.41
    لي
    0.41
    ون
    0.40
    POSITIVE LOGITS
    ἱ
    0.50
    ⛅
    0.48
     καθη
    0.47
    *;
    0.46
     εμπ
    0.46
     indestructible
    0.46
     чыныгы
    0.46
    📫
    0.46
    μβρίου
    0.45
    outube
    0.45
    Activations Density 0.001%

    No Known Activations