© 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. 439
    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
    ת
    1.52
    у
    1.50
    ים
    1.45
    ться
    1.34
    ות
    1.34
    ا
    1.30
     milliamperes
    1.27
    ের
    1.26
    ли
    1.26
    т
    1.25
    POSITIVE LOGITS
     pamoja
    1.21
    bian
    1.16
    ty
    1.16
    tting
    1.15
    daki
    1.08
    il
    1.07
    g
    1.07
    chen
    1.02
     przypadku
    1.01
    倆
    1.01
    Activations Density 1.240%

    No Known Activations