© 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. 254531
    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
    楹
    0.54
    ային
    0.54
    劑
    0.54
    顯示
    0.49
    居民
    0.48
    蒴
    0.46
    戰
    0.45
    雀
    0.45
    員工
    0.44
    是最
    0.44
    POSITIVE LOGITS
     ava
    0.53
    讐
    0.50
    ien
    0.49
     ia
    0.48
     img
    0.47
     их
    0.46
     웃
    0.46
     hulls
    0.45
     ekip
    0.45
     eki
    0.45
    Activations Density 0.001%

    No Known Activations