© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 229
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    ﻝ
    0.74
    ﻭ
    0.70
     minify
    0.70
    ﺭ
    0.69
    ﻉ
    0.69
     mostrar
    0.68
     perone
    0.66
     joten
    0.66
     pediu
    0.66
     kiu
    0.66
    POSITIVE LOGITS
    ق
    0.76
    лно
    0.62
    zelfde
    0.57
    kiej
    0.57
    ר
    0.56
    лни
    0.55
    ح
    0.53
    ו
    0.52
    ע
    0.52
    zione
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.