© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1749
    Prev
    Next
    INDEX
    Explanations

    offering alternatives instead of harmful content

    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_13_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
    онер
    1.10
    pendicular
    1.06
    вед
    1.03
    蛐
    1.01
    ่าน
    0.95
    ат
    0.94
    мар
    0.94
     эм
    0.93
    蛔
    0.93
    oyloxy
    0.93
    POSITIVE LOGITS
     आवश्यकताओं
    1.38
     semuanya
    1.30
     semua
    1.25
     sepenuhnya
    1.21
     seç
    1.17
     tugas
    1.15
     zamów
    1.15
     Purification
    1.14
     tốt
    1.14
     Zustimmung
    1.14
    Activations Density 0.009%

    No Known Activations