© 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. 7-GEMMASCOPE-2-RES-16K
    7. 726
    Prev
    Next
    INDEX
    Explanations

    age levels populations energy statements

    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
    党
    2.08
     শুভেচ্ছা
    2.08
    nommen
    2.02
    спользу
    1.98
     gep
    1.97
     нажа
    1.94
     benutzt
    1.93
     espè
    1.92
     goma
    1.92
    驻
    1.90
    POSITIVE LOGITS
     buildings
    2.63
     bangunan
    2.49
     dwellings
    2.47
     residential
    2.45
    建物
    2.38
     домов
    2.36
     mansions
    2.35
     edificios
    2.34
     viviendas
    2.34
     Residential
    2.30
    Activations Density 0.919%

    No Known Activations