© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7789
    Prev
    Next
    INDEX
    Explanations

    .com/app

    np_acts-logits-general · gemini-2.5-flash-lite

    dense academic/technical prose, especially with quantitative or economics/science terminology and formal, jargon-heavy phrasing.

    oai_token-act-pair · gpt-5Triggered by @limichellelm
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     你
    1.54
     θ
    1.52
     】
    1.44
     （
    1.40
    】
    1.38
     g
    1.35
     我们
    1.33
     平
    1.32
     这里
    1.31
     或者
    1.31
    POSITIVE LOGITS
    ucin
    1.09
    ushman
    1.02
    acce
    1.00
    azia
    0.99
    ierne
    0.97
    ierenden
    0.96
    ynyt
    0.96
    icile
    0.95
    ieren
    0.95
    astaan
    0.95
    Activations Density 0.536%

    No Known Activations