© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 1859
    Prev
    Next
    INDEX
    Explanations

    JSX syntax for UI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     Artifact
    1.21
     manière
    1.07
     Additionally
    1.05
     因此
    1.05
     パ
    1.05
     配置
    1.04
     Relationships
    1.02
     ジ
    1.02
     Mastery
    1.00
     然后
    1.00
    POSITIVE LOGITS
     blamed
    1.09
    commended
    1.03
    illegal
    1.01
    osw
    1.01
    imported
    1.00
    biggest
    1.00
     boon
    0.99
    urlString
    0.99
     crippling
    0.99
    နိုင်ငံ
    0.97
    Activations Density 0.053%

    No Known Activations