© 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. 13648
    Prev
    Next
    INDEX
    Explanations

    seeking reasons and explanations

    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
     Trước
    1.79
     környez
    1.76
     除了
    1.67
     忄
    1.62
    㤈
    1.61
     buildTypes
    1.60
     dziew
    1.59
    秅
    1.59
     কারখানা
    1.58
     उद्योगों
    1.58
    POSITIVE LOGITS
    ogue
    1.44
    ully
    1.37
    uerre
    1.36
    great
    1.33
    appropriate
    1.32
    ulse
    1.29
    ogu
    1.25
     worthy
    1.24
    efficient
    1.23
    oren
    1.22
    Activations Density 0.090%

    No Known Activations