© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 887
    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_22_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
     Anda
    1.23
    ⁣
    1.19
     आपका
    1.16
     Ihrem
    1.15
    உங்கள்
    1.15
     •
    1.08
    
    1.08
    ���
    1.06
     Ihre
    1.06
     quarks
    1.05
    POSITIVE LOGITS
     것이다
    1.14
     있다
    1.07
    있다
    1.03
    ；
    0.98
     shortcoming
    0.98
     thing
    0.96
    것
    0.96
     있었다
    0.96
     എന്നു
    0.95
     être
    0.93
    Activations Density 0.197%

    No Known Activations