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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 755
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    菏
    1.48
     centroids
    1.39
     lỗ
    1.37
    operating
    1.33
    variables
    1.32
    jdbcType
    1.32
    阻塞
    1.30
    default
    1.29
    }=\
    1.29
    values
    1.29
    POSITIVE LOGITS
     anthology
    2.46
     masterpiece
    2.21
     berjudul
    2.21
     álbum
    2.19
     trilogy
    2.19
     romanzo
    2.14
     novels
    2.09
     작품
    2.01
     masterful
    1.99
     album
    1.97
    Activations Density 3.795%

    No Known Activations