© 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. 13-GEMMASCOPE-2-RES-16K
    7. 13583
    Prev
    Next
    INDEX
    Explanations

    lack of access or abilities

    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
     fadeInUp
    1.66
     hồn
    1.57
    
    1.54
     
    1.52
     โร
    1.51
     краса
    1.49
     glic
    1.49
    
    1.47
     Ð
    1.47
     ด้าน
    1.46
    POSITIVE LOGITS
    sofar
    1.34
     spacetime
    1.27
    みたいな
    1.23
     subset
    1.22
     arbitr
    1.16
     temporally
    1.16
     nuk
    1.14
     instantiated
    1.13
    噉
    1.13
    irected
    1.12
    Activations Density 0.169%

    No Known Activations