© 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. 10901
    Prev
    Next
    INDEX
    Explanations

    medical condition URLs or shell script 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
     pake
    0.93
     Pháp
    0.89
     Surya
    0.89
     笑
    0.89
    呂
    0.87
     měst
    0.84
     référence
    0.84
     kuasa
    0.82
    झ
    0.82
    個
    0.81
    POSITIVE LOGITS
    vari
    0.90
    Vari
    0.88
     anhydrous
    0.85
    Corner
    0.84
    נע
    0.83
    Calle
    0.81
    ائے
    0.80
    idata
    0.80
     stint
    0.79
    adn
    0.79
    Activations Density 0.020%

    No Known Activations