© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14624
    Prev
    Next
    INDEX
    Explanations

    l-typed brackets

    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
    ന്‍
    2.15
    კო
    2.05
    ipino
    1.94
    )}^
    1.94
     enqu
    1.93
     Фургала
    1.92
    ⁽
    1.91
     kelu
    1.91
    ClF
    1.89
    
    1.89
    POSITIVE LOGITS
    ோருக்கு
    2.14
    versi
    2.04
     HUGE
    1.96
     وقل
    1.95
    කාශ
    1.94
     Eindruck
    1.92
     caut
    1.89
    jà
    1.86
     Flight
    1.82
     Space
    1.81
    Activations Density 0.021%

    No Known Activations