© 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. 254654
    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
    련
    0.46
    vió
    0.45
    ँग
    0.43
    職員
    0.42
     broadcasting
    0.41
    ění
    0.41
    QWidget
    0.41
     лигасы
    0.40
    тво
    0.40
    це
    0.39
    POSITIVE LOGITS
     πλα
    0.54
    ie
    0.47
    HeaderParams
    0.47
    椇
    0.46
     ทด
    0.44
     ଗ
    0.44
     帽
    0.44
    ตี
    0.43
    zied
    0.43
    គ្រ
    0.42
    Activations Density 0.001%

    No Known Activations