© 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. 417
    Prev
    Next
    INDEX
    Explanations

    aims and strives

    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
     délai
    1.40
     図
    1.39
     REACTIONS
    1.37
     terminado
    1.35
     izgled
    1.31
    完毕
    1.30
     disappearing
    1.30
     ...]
    1.29
     izgleda
    1.29
     cicat
    1.28
    POSITIVE LOGITS
     strives
    1.47
     strive
    1.45
     aim
    1.38
     aims
    1.29
     specialise
    1.27
     specialize
    1.26
     pioneered
    1.26
     endeav
    1.22
     focuses
    1.20
    致力
    1.20
    Activations Density 5.737%

    No Known Activations