© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11630
    Prev
    Next
    INDEX
    Explanations

    qualified negation

    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_7_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
    𝗜
    2.70
     surmounted
    2.68
     când
    2.64
     Ди
    2.63
     ######
    2.60
     ก
    2.59
     ทํา
    2.59
     ![](
    2.51
    roix
    2.50
    𝗘
    2.50
    POSITIVE LOGITS
    legen
    2.69
    wirk
    2.66
    ymes
    2.64
    kö
    2.56
    ysty
    2.55
    ätten
    2.54
     sodass
    2.54
    öre
    2.54
    weis
    2.50
    legt
    2.49
    Activations Density 0.011%

    No Known Activations