© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1809
    Prev
    Next
    INDEX
    Explanations

    represents a

    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
    se
    1.87
     premise
    1.85
    θ
    1.81
     le
    1.81
    actic
    1.80
    मिक
    1.78
    lys
    1.75
    nger
    1.75
    บค้น
    1.71
    cht
    1.68
    POSITIVE LOGITS
     representación
    2.50
    ativeness
    2.43
    antd
    2.28
    ReactDOM
    2.28
     //{
    2.21
    asında
    2.18
    ্ভব
    2.18
     imgSrc
    2.16
    GetObject
    2.15
     représenter
    2.14
    Activations Density 0.300%

    No Known Activations