© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11134
    Prev
    Next
    INDEX
    Explanations

    SQL command and its equivalent

    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
     thisComponent
    2.80
    जीशन
    2.54
    
    2.48
    មើ
    2.44
    кло
    2.36
    zął
    2.35
    โรค
    2.34
    𝐟
    2.33
     चूंकि
    2.33
    ய்ப்ப
    2.31
    POSITIVE LOGITS
    em
    2.30
    োজন
    2.11
    respect
    2.05
    dataSource
    2.00
     stick
    1.96
    ārt
    1.95
    ంగ్‌
    1.91
    റി
    1.87
    ěz
    1.83
    angles
    1.82
    Activations Density 0.000%

    No Known Activations