© 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. 22-GEMMASCOPE-2-RES-16K
    7. 303
    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
    loo
    0.66
    dem
    0.60
     ;
    0.59
    。)
    0.59
     latter
    0.58
    yrıca
    0.58
     cult
    0.58
    icho
    0.58
     aim
    0.57
     •
    0.57
    POSITIVE LOGITS
    ="
    1.53
    =\"
    1.48
    ='
    1.47
    =”
    1.43
    ="@
    1.33
    ="",
    1.33
    ="$
    1.29
    ={
    1.29
    ="{
    1.28
    ={'
    1.27
    Activations Density 0.410%

    No Known Activations