© 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. 3540
    Prev
    Next
    INDEX
    Explanations

    comparing two items

    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
     espera
    1.55
    äng
    1.55
    ður
    1.46
     Bakufu
    1.35
    を迎
    1.35
    鴿
    1.35
    slaught
    1.34
    ða
    1.32
    пону
    1.32
    дати
    1.31
    POSITIVE LOGITS
    ----\
    1.43
    貅
    1.40
    Smiling
    1.37
     biosynthesis
    1.37
     totalSupply
    1.37
    --*/
    1.37
    atributo
    1.32
    职责
    1.31
    Shared
    1.31
    Connections
    1.30
    Activations Density 0.003%

    No Known Activations