© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12691
    Prev
    Next
    INDEX
    Explanations

    testing, database calls, and logic

    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_13_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
    鍦
    1.96
    
    1.90
     logro
    1.89
    
    1.86
     pobres
    1.85
    норийска
    1.83
    
    1.79
    放棄
    1.77
     appetite
    1.77
     pobre
    1.75
    POSITIVE LOGITS
     heads
    1.40
     Heads
    1.36
    ة
    1.24
    heads
    1.20
     (
    1.18
     DataLoader
    1.14
    C
    1.10
     związ
    1.09
    दायक
    1.09
    fulness
    1.09
    Activations Density 0.000%

    No Known Activations