© 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. 10797
    Prev
    Next
    INDEX
    Explanations

    prone to errors, distortion, noise

    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
    widget
    1.22
    ជី
    1.08
    billed
    1.06
    大型
    1.04
    बॉक्स
    1.04
    鹼
    1.03
    profits
    1.03
    数据显示
    1.03
    reverse
    1.02
    小說
    1.01
    POSITIVE LOGITS
    *.
    1.04
     ought
    0.99
    '.
    0.92
     *.
    0.89
     needful
    0.89
     fulfil
    0.88
    **.
    0.87
     prese
    0.87
    ".
    0.85
     needs
    0.85
    Activations Density 0.147%

    No Known Activations