© 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. 258846
    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
    mallow
    0.54
    窈
    0.52
    R
    0.48
    roids
    0.48
    eritud
    0.46
    pink
    0.45
    H
    0.45
    MAR
    0.45
    Ener
    0.44
    X
    0.44
    POSITIVE LOGITS
     zmniejs
    0.50
     Emile
    0.47
     Михай
    0.46
     حسين
    0.46
    agamanam
    0.45
    ائيل
    0.45
    埆
    0.45
     Михаил
    0.45
     Jednak
    0.45
     afecta
    0.44
    Activations Density 0.001%

    No Known Activations