© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 27
    Prev
    Next
    INDEX
    Explanations

    based on

    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
     Rok
    0.89
     Domb
    0.86
     Hong
    0.82
    2
    0.82
     Ceb
    0.82
     HK
    0.80
     BOD
    0.76
     Soren
    0.76
     Stok
    0.76
    Hong
    0.76
    POSITIVE LOGITS
    erad
    0.89
     Walla
    0.87
    砝
    0.84
     Traveller
    0.82
     Ellie
    0.82
     Haar
    0.81
     Carleton
    0.81
     Wendell
    0.80
     prét
    0.80
    Carr
    0.79
    Activations Density 8.658%

    No Known Activations