© 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. 14858
    Prev
    Next
    INDEX
    Explanations

    #include <

    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
    																		
    2.25
    ナップ
    2.17
    BUST
    2.15
    																														
    2.15
    																										
    2.13
     TRIP
    2.10
    dfunding
    2.07
    おり
    2.04
    宕
    2.03
     Strecke
    2.03
    POSITIVE LOGITS
    آ
    1.76
    ВА
    1.74
    iyot
    1.63
     professionally
    1.60
    inare
    1.59
    anzia
    1.58
    ا
    1.58
    Ц
    1.57
    мов
    1.55
    جو
    1.54
    Activations Density 0.017%

    No Known Activations