© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    linking and connection

    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_17_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
    ulz
    0.96
    vori
    0.90
     Kombination
    0.89
    nata
    0.89
    ULS
    0.89
     acompañada
    0.89
    يرا
    0.88
    깝
    0.86
     finde
    0.86
     naro
    0.86
    POSITIVE LOGITS
     between
    1.12
     между
    0.98
     끊
    0.95
     বিচ্ছিন্ন
    0.93
     established
    0.92
    between
    0.92
    맺
    0.92
     Between
    0.90
    established
    0.87
    ข้อง
    0.86
    Activations Density 0.620%

    No Known Activations