© 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. 257408
    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
     ಹೃದಯ
    0.54
    綏
    0.47
    ઞ
    0.47
     ordinances
    0.45
     ufficiale
    0.45
    wam
    0.44
    ablus
    0.44
     alot
    0.44
    HAND
    0.44
     aggravate
    0.44
    POSITIVE LOGITS
    $
    0.54
     =$
    0.48
     gerçekleş
    0.48
     savoury
    0.46
     genannten
    0.45
     réalisée
    0.45
    െടുത്തു
    0.44
    iód
    0.44
    $('
    0.44
     térmica
    0.43
    Activations Density 0.000%

    No Known Activations