© 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. 4994
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
     делу
    0.94
     Hamlin
    0.92
    routeName
    0.87
     merk
    0.87
    ropoda
    0.86
     nvidia
    0.84
    洽
    0.83
    referrer
    0.81
     конференции
    0.81
     treatise
    0.81
    POSITIVE LOGITS
     counc
    1.57
    ))$
    1.50
     хвати
    1.47
    ))`
    1.45
    leur
    1.44
    掸
    1.44
    均匀
    1.43
    แนน
    1.41
    عيب
    1.37
    iação
    1.36
    Activations Density 0.057%

    No Known Activations