© 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. 12329
    Prev
    Next
    INDEX
    Explanations

    khan academy math science computing

    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
    ,((
    1.99
     Gmail
    1.96
     홍
    1.94
     gmail
    1.93
     google
    1.92
     교통
    1.86
     mucosa
    1.84
     ecommerce
    1.82
     ',',
    1.81
     Google
    1.81
    POSITIVE LOGITS
    S
    1.25
     бъде
    1.19
     futuras
    1.08
     futurs
    1.07
    Y
    1.05
    B
    1.04
    จะได้
    1.04
    duire
    0.98
    M
    0.98
    R
    0.98
    Activations Density 0.562%

    No Known Activations