© 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. 393
    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
    tól
    1.24
    та
    1.12
    ー
    1.09
    ो
    1.05
    ah
    1.04
    我想
    1.04
    iance
    1.03
    ์
    1.00
    出来る
    0.98
    Incidentally
    0.98
    POSITIVE LOGITS
     whereupon
    1.32
    적으로
    1.22
    bath
    1.05
    ity
    1.05
    ח
    1.02
    idade
    0.99
    ną
    0.99
    لی
    0.98
    szer
    0.95
     thereupon
    0.95
    Activations Density 1.384%

    No Known Activations