© 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. 3920
    Prev
    Next
    INDEX
    Explanations

    Drinking, controlled, beginnings

    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
    imy
    1.14
     Moya
    1.13
     ikat
    1.12
    iley
    1.11
    ̑
    1.10
    タグ
    1.08
     dicion
    1.07
    鞆
    1.06
     pude
    1.06
     jur
    1.06
    POSITIVE LOGITS
    Welcome
    1.43
     Welcome
    1.41
    welcome
    1.24
    曙
    1.16
    WELCOME
    1.13
     welcome
    1.11
    elcome
    1.07
    pherds
    1.06
     Compass
    1.05
     Glowing
    1.05
    Activations Density 0.121%

    No Known Activations