© 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. 16-GEMMASCOPE-2-RES-16K
    7. 439
    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_16_width_16k_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
    in
    1.07
    ↵
    0.99
    ل
    0.86
    is
    0.80
    ات
    0.80
    ام
    0.76
    де
    0.71
    मध्ये
    0.71
    ز
    0.70
    ب
    0.70
    POSITIVE LOGITS
     a
    0.76
    нер
    0.63
    ことを
    0.61
    ן
    0.60
    ﺪ
    0.58
    ી
    0.57
    ﻚ
    0.57
    人
    0.56
    ía
    0.55
    тур
    0.55
    Activations Density 9.084%

    No Known Activations