© 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. 9841
    Prev
    Next
    INDEX
    Explanations

    install, run, verify commands

    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
     Truly
    1.01
     非常
    0.99
     Completely
    0.99
     Hardly
    0.98
     我們
    0.98
     Totally
    0.97
     身
    0.97
    akings
    0.96
    completely
    0.95
     wholly
    0.95
    POSITIVE LOGITS
    Rüyada
    0.88
    |");
    0.86
     společnosti
    0.84
     cuentan
    0.80
     permettent
    0.80
    Kit
    0.78
    rasında
    0.78
    ='';
    0.75
     apresentam
    0.72
     lehetős
    0.72
    Activations Density 0.110%

    No Known Activations