© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 221
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ассорти
    0.94
     сприя
    0.91
    Burg
    0.91
    Marin
    0.91
     کمپیو
    0.91
    phthalm
    0.90
    Gab
    0.90
    魟
    0.87
    urban
    0.85
    camiseta
    0.85
    POSITIVE LOGITS
     object
    1.08
     instance
    1.01
     namespace
    1.00
     constructor
    0.98
     function
    0.97
     value
    0.97
     objects
    0.96
     attribute
    0.96
     callback
    0.95
     callable
    0.94
    Activations Density 1.228%

    No Known Activations