© 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. 252602
    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
     cardiomyocytes
    0.55
    ExpNow
    0.49
    hf
    0.49
    ۱۰
    0.49
    </tfoot>
    0.46
    Hfn
    0.46
     LOTRAchievement
    0.46
    িশালী
    0.46
    }{$
    0.46
    Hundred
    0.45
    POSITIVE LOGITS
     has
    0.56
     Piem
    0.53
    نس
    0.52
     Brasil
    0.52
     Debbie
    0.52
     Ladies
    0.52
     Presidente
    0.51
    has
    0.50
     is
    0.49
     Leg
    0.48
    Activations Density 0.001%

    No Known Activations