© 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. 10565
    Prev
    Next
    INDEX
    Explanations

    3 8

    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
    י
    2.33
    𝑖
    2.32
     Pathol
    2.24
     จํานวน
    2.19
    𝑒
    2.16
    而言
    2.09
    𝑟
    2.07
    ينا
    2.05
    𝑣
    2.05
    ,’
    2.04
    POSITIVE LOGITS
    ´
    2.65
    `
    2.27
    ত্বের
    2.25
    ‟
    2.14
    ত্ব
    2.00
    ção
    1.96
     fech
    1.95
    '
    1.94
     #"
    1.89
     igreja
    1.86
    Activations Density 0.047%

    No Known Activations