© 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. 825
    Prev
    Next
    INDEX
    Explanations

    VBA, Human, Lanikai, Compact, Variance

    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
    －
    1.32
    global
    1.29
     lifespan
    1.28
    ibli
    1.21
     embedded
    1.19
     near
    1.19
     timescale
    1.19
    သက်
    1.19
     embeds
    1.18
     exerts
    1.16
    POSITIVE LOGITS
    ARAJYA
    2.00
     پہا
    1.97
    Я
    1.93
     Thiết
    1.93
    Й
    1.92
    Ỡ
    1.91
    There
    1.89
     ا
    1.88
     Bây
    1.87
    녕하십니까
    1.87
    Activations Density 0.172%

    No Known Activations