© 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. 258016
    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
    涌
    0.60
     Whitehead
    0.47
     dyed
    0.47
     цвето
    0.47
    浆
    0.44
     faded
    0.43
     Hazel
    0.43
     Cherry
    0.43
     Brandt
    0.42
     cherry
    0.42
    POSITIVE LOGITS
     fok
    0.49
    pho
    0.49
    ある
    0.48
     connue
    0.47
     fournisseur
    0.47
     vérifier
    0.47
     شناخته
    0.47
    .*?
    0.46
    gub
    0.45
    ーー
    0.45
    Activations Density 0.000%

    No Known Activations