© 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. 1547
    Prev
    Next
    INDEX
    Explanations

    political economic and social concepts

    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
    hmen
    0.98
    وون
    0.97
    ocular
    0.92
    ્ષ
    0.92
    tough
    0.91
    ត់
    0.91
    ්
    0.90
    қда
    0.89
    еру
    0.89
     truly
    0.89
    POSITIVE LOGITS
    LI
    0.91
     Campe
    0.89
     Useful
    0.88
    {{{
    0.87
    )<<
    0.87
     zeuden
    0.86
    ทรวง
    0.86
    ))+
    0.86
    ILI
    0.86
    ALE
    0.83
    Activations Density 0.000%

    No Known Activations