© 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. 258111
    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
     किन्तु
    0.51
    ;"
    0.50
     cared
    0.49
    artifact
    0.48
    izes
    0.47
     corresponds
    0.47
     promedio
    0.47
     किंतु
    0.46
     notoriously
    0.45
     derivadas
    0.45
    POSITIVE LOGITS
    بل
    0.55
    رفت
    0.48
    కోండి
    0.48
     வைத்திருக்க
    0.48
    缔
    0.47
    őd
    0.47
    umus
    0.47
    راج
    0.46
    憤
    0.46
     Tattoo
    0.46
    Activations Density 0.001%

    No Known Activations