© 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. 615
    Prev
    Next
    INDEX
    Explanations

    okay, please

    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
    äter
    1.70
     Fälle
    1.68
     것입니다
    1.68
    əl
    1.65
    <unused373>
    1.61
    侶
    1.61
     Notably
    1.60
     \%)$,
    1.58
     underpinned
    1.58
    함으로써
    1.58
    POSITIVE LOGITS
    Hello
    1.53
    Hallo
    1.50
    Alright
    1.50
     congrats
    1.46
    Hi
    1.44
    Nice
    1.40
    楼主
    1.38
    Edit
    1.34
    yeah
    1.32
    Wow
    1.31
    Activations Density 0.818%

    No Known Activations