© 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. 252432
    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
     atth
    0.47
     Regularly
    0.46
     Lij
    0.46
    ిన
    0.45
    ித்த
    0.44
    ப்பட்டி
    0.43
    険
    0.43
     Sachin
    0.43
    لی
    0.43
     колеба
    0.43
    POSITIVE LOGITS
    ，
    0.49
    据
    0.47
    pubescens
    0.46
    off
    0.45
    hu
    0.44
    odes
    0.44
    ipment
    0.44
    ops
    0.43
    фы
    0.43
    STORAGE
    0.43
    Activations Density 0.002%

    No Known Activations