© 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. 259382
    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
     corroborated
    0.47
    otted
    0.45
    otest
    0.44
    ogenous
    0.42
    orschung
    0.41
     Zoll
    0.41
    ܨ
    0.41
    დ
    0.41
    arms
    0.41
    ằm
    0.41
    POSITIVE LOGITS
     Restoration
    0.54
     espectadores
    0.50
     Tina
    0.48
     repair
    0.48
     مع
    0.46
     دیگر
    0.46
     Repair
    0.45
     raref
    0.45
     restorations
    0.45
    park
    0.45
    Activations Density 0.003%

    No Known Activations