© 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. 494
    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
    ت
    1.16
    ר
    1.11
    ل
    1.04
    er
    1.03
    ف
    1.02
    o
    0.96
    ق
    0.96
    ed
    0.93
    1
    0.93
    ان
    0.91
    POSITIVE LOGITS
    ς
    1.22
    s
    1.06
     outliers
    1.04
    ের
    1.00
    ਆਂ
    0.93
    ség
    0.88
    瘩
    0.87
    者は
    0.85
    因為
    0.84
    sPath
    0.82
    Activations Density 1.550%

    No Known Activations