© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10371
    Prev
    Next
    INDEX
    Explanations

    gain, bandwidth, filtering, noise, amplifier

    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
    Brightness
    0.93
    okinase
    0.89
    鐳
    0.89
    亮度
    0.87
     बिट
    0.86
     Ultraviolet
    0.84
     ಡಿ
    0.83
    燦
    0.83
    쭌
    0.83
     isomerization
    0.83
    POSITIVE LOGITS
    🐄
    1.09
     parasit
    1.08
    🐏
    1.04
     Mie
    1.03
     Zo
    1.01
     CST
    0.99
     Feeding
    0.99
    🌵
    0.99
     induct
    0.98
    🐮
    0.98
    Activations Density 0.191%

    No Known Activations