© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7683
    Prev
    Next
    INDEX
    Explanations

    incoming request

    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
    વ
    1.19
     этой
    1.19
     આ
    1.19
     еще
    1.18
     وك
    1.12
     મ
    1.09
     ક
    1.08
     vườn
    1.07
     أيام
    1.06
     એ
    1.05
    POSITIVE LOGITS
     co
    0.91
     ve
    0.83
    ̃
    0.83
     vo
    0.83
    ಐ
    0.83
    との
    0.82
    
    0.79
    iec
    0.79
     lieu
    0.78
    
    0.77
    Activations Density 0.012%

    No Known Activations