© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2737
    Prev
    Next
    INDEX
    Explanations

    I understand or know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    !")
    2.02
    %")
    1.92
    ?!"
    1.92
     shit
    1.87
    ]+")
    1.86
     haha
    1.83
    ?")
    1.80
     soooo
    1.76
    .")
    1.74
     kiddos
    1.73
    POSITIVE LOGITS
     kier
    0.99
    ليف
    0.98
     Concern
    0.97
    dien
    0.97
    جام
    0.91
     изучения
    0.90
    亲
    0.89
    体
    0.88
    aspx
    0.86
    满意
    0.85
    Activations Density 0.083%

    No Known Activations