© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6772
    Prev
    Next
    INDEX
    Explanations

    therapists

    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
    European
    1.37
     أوروب
    1.35
     pennies
    1.30
     яс
    1.30
     European
    1.28
     proverbial
    1.28
     الأوروب
    1.27
    낯
    1.27
    entities
    1.26
     العناصر
    1.26
    POSITIVE LOGITS
     remove
    1.85
     execute
    1.78
     prepare
    1.77
     get
    1.76
     render
    1.75
     configure
    1.69
     rendere
    1.69
     make
    1.67
     retrieve
    1.66
     recover
    1.63
    Activations Density 0.181%

    No Known Activations