© 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. 22-GEMMASCOPE-2-RES-16K
    4. 9884
    Prev
    Next
    INDEX
    Explanations

    clothing and temperature

    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
     naturellement
    0.99
     ന
    0.92
    addListener
    0.91
    '=>'
    0.90
     directional
    0.89
    arum
    0.88
    髂
    0.87
    參考
    0.87
     dados
    0.87
    জ্ঞা
    0.85
    POSITIVE LOGITS
    For
    1.09
    Ε
    1.03
    EL
    1.03
    FIRE
    1.02
    EDA
    1.01
    And
    1.00
    Yaw
    1.00
    Hil
    0.99
    
    0.99
     বিলম্ব
    0.98
    Activations Density 0.000%

    No Known Activations