© 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. 2260
    Prev
    Next
    INDEX
    Explanations

    your code/application

    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
    댔
    0.80
     Atwood
    0.78
    太太
    0.77
    둡
    0.77
     Sanderson
    0.76
    idavit
    0.76
    laughter
    0.76
     Stephens
    0.75
    햅
    0.72
    യ്യ
    0.71
    POSITIVE LOGITS
    ский
    1.00
     ПО
    0.96
     PO
    0.94
     ZA
    0.92
     ZIP
    0.91
     zip
    0.91
    AE
    0.90
     записи
    0.86
    Try
    0.85
    ETER
    0.85
    Activations Density 0.262%

    No Known Activations