© 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. 12-GEMMASCOPE-2-RES-16K
    7. 6641
    Prev
    Next
    INDEX
    Explanations

    negation and exclusion

    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_12_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
     anytime
    1.95
    conferences
    1.88
     equating
    1.86
    prits
    1.81
     fingers
    1.81
     quên
    1.77
     quickest
    1.76
     숫
    1.74
    每一次
    1.74
     anys
    1.73
    POSITIVE LOGITS
    ental
    1.29
    が含ま
    1.29
    ]")]
    1.27
     Covered
    1.25
    ivi
    1.24
     входит
    1.23
    ernel
    1.23
    ուն
    1.23
    含む
    1.22
     elementy
    1.22
    Activations Density 0.130%

    No Known Activations