© 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. 255456
    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
     preservatives
    0.47
     Reserva
    0.43
    萸
    0.42
     polyclonal
    0.41
     dispensers
    0.41
     Pasteur
    0.41
     Convey
    0.39
     fratern
    0.39
     पेय
    0.39
     Mayo
    0.39
    POSITIVE LOGITS
     nồi
    0.59
    鍋
    0.51
    锅
    0.49
     cookware
    0.47
    솥
    0.45
    cook
    0.44
     cooker
    0.44
     poth
    0.43
     bonnet
    0.43
    ARTS
    0.43
    Activations Density 0.079%

    No Known Activations