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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8914
    Prev
    Next
    INDEX
    Explanations

    equality or comparison

    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
     বঙ্গবন্ধ
    0.98
    Into
    0.98
    cleaning
    0.95
    IOC
    0.95
    潰
    0.91
    皇
    0.90
    飯
    0.87
    觀察
    0.87
     જેને
    0.87
    сль
    0.87
    POSITIVE LOGITS
    itarian
    1.22
     তালে
    1.16
     spaced
    1.15
    led
    1.14
     нулю
    1.10
     temperament
    1.09
    opportunity
    1.04
     păr
    1.04
     distribuzione
    1.03
    ार्थक
    1.03
    Activations Density 0.086%

    No Known Activations