© 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. 3591
    Prev
    Next
    INDEX
    Explanations

    challenges and requirements

    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
     ошиб
    1.75
     fooling
    1.62
    过了
    1.60
    ocop
    1.57
     worthless
    1.56
     juist
    1.54
    搽
    1.50
     invented
    1.49
    ＝＝
    1.47
     bygone
    1.46
    POSITIVE LOGITS
     richied
    1.19
    Weitere
    1.15
     Require
    1.14
     предполага
    1.11
     Requ
    1.10
     требует
    1.09
    версите
    1.08
     Dine
    1.07
    мию
    1.03
    Requ
    1.01
    Activations Density 0.147%

    No Known Activations