© 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. 486
    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
     공간
    1.16
     dạng
    1.11
    黏
    1.09
     livelli
    1.08
     usuario
    1.06
     분포
    1.04
     느낌
    1.04
     使い
    1.04
    ஔ
    1.04
     체험
    1.03
    POSITIVE LOGITS
     undertaken
    0.99
     unanimously
    0.99
     aftermath
    0.97
     announced
    0.92
     impasse
    0.92
     instigated
    0.92
     debacle
    0.91
     imposed
    0.91
     unjust
    0.90
     overwhelmingly
    0.89
    Activations Density 1.806%

    No Known Activations