© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14659
    Prev
    Next
    INDEX
    Explanations

    offshore, imported, geos

    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
    ist
    2.77
    і
    2.56
    ిన
    2.47
    াস
    2.31
    end
    2.18
     qualify
    2.15
    کنندگان
    2.13
    的に
    2.04
     bleed
    2.02
     ble
    2.01
    POSITIVE LOGITS
    此之外
    3.22
    yó
    3.21
    ר
    3.08
    aop
    2.94
    нский
    2.94
    erà
    2.88
    oq
    2.83
    י
    2.82
     geomét
    2.82
    aidh
    2.81
    Activations Density 0.002%

    No Known Activations