© 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. 10564
    Prev
    Next
    INDEX
    Explanations

    systemd and Vegetables

    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
    luss
    0.87
     reproduce
    0.84
     ruling
    0.84
    ذن
    0.83
    吕
    0.83
     原子
    0.82
    ওয়ার
    0.82
    agogue
    0.82
     yön
    0.81
    क्राइब
    0.81
    POSITIVE LOGITS
    시킨
    0.96
    ínas
    0.94
    ssia
    0.91
     pept
    0.87
    시키
    0.87
    ﺃ
    0.85
    AIS
    0.84
    สุขภาพ
    0.83
    wnież
    0.83
    გორ
    0.82
    Activations Density 0.022%

    No Known Activations