© 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. 11918
    Prev
    Next
    INDEX
    Explanations

    Margaret Thatcher

    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
    ･･･
    2.11
    ύ
    2.06
    ὼ
    2.04
    .."
    2.01
     fielder
    1.99
    iguë
    1.96
    徵
    1.96
    …"
    1.96
    ..."
    1.93
     WH
    1.93
    POSITIVE LOGITS
    <h4>
    1.95
    <h5>
    1.79
    Bread
    1.76
    حدة
    1.71
     شبکه
    1.66
    ার্ড
    1.64
    FactoryBean
    1.63
    Recipient
    1.60
    ,{
    1.59
    젖
    1.59
    Activations Density 0.010%

    No Known Activations