© 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
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9521
    Prev
    Next
    INDEX
    Explanations

    employer/employee/problem

    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_22_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
     Durchschnitt
    1.15
    produkte
    1.05
     પ્રસ
    1.03
    cześ
    0.98
    儅
    0.97
    섭
    0.97
     imediat
    0.97
    쨍
    0.96
    뎐
    0.95
     நிகழ்ச்ச
    0.93
    POSITIVE LOGITS
     Gutenberg
    1.61
    iles
    1.32
    euler
    1.29
    ILE
    1.29
    经理
    1.28
    management
    1.27
    Euler
    1.26
     management
    1.25
    ile
    1.23
     Euler
    1.17
    Activations Density 0.063%

    No Known Activations