© 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. 259043
    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
     extraordinarily
    0.52
    尼亚
    0.50
    Ę
    0.48
    ۲
    0.47
    dı
    0.47
    ţiile
    0.47
    2
    0.47
    Daniels
    0.46
    晃
    0.45
     exceedingly
    0.45
    POSITIVE LOGITS
     ਵ
    0.54
     달
    0.53
     တ
    0.52
     ไ
    0.50
     아
    0.50
     요
    0.48
     ਮ
    0.48
     ମ
    0.48
     식
    0.48
     з
    0.46
    Activations Density 0.000%

    No Known Activations