© 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. 10073
    Prev
    Next
    INDEX
    Explanations

    sun and light

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     terakhir
    0.90
     везде
    0.89
    >{
    0.86
     (>
    0.85
    =[
    0.85
     dahulu
    0.85
     여기가
    0.84
     whichever
    0.83
     $>
    0.83
    らが
    0.83
    POSITIVE LOGITS
     Jamie
    1.03
     Jia
    1.01
     Juan
    0.96
     Jimin
    0.95
    Jamie
    0.90
     subjected
    0.90
     Australian
    0.89
     UNITED
    0.89
    ଝ
    0.88
    Juan
    0.87
    Activations Density 0.074%

    No Known Activations