© 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. 17-GEMMASCOPE-2-RES-16K
    7. 200
    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_17_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
    ismatch
    1.59
     periodistas
    1.58
     chunky
    1.55
    comboBox
    1.54
    嗆
    1.53
    flowLayoutPanel
    1.51
     경쟁
    1.50
     linkCell
    1.50
     bulky
    1.49
    嘁
    1.48
    POSITIVE LOGITS
     Divine
    3.12
     spiritual
    3.09
     divine
    3.08
     God
    3.02
     Spiritual
    3.00
    spiritual
    2.84
    Divine
    2.81
     spiritually
    2.73
     하나님
    2.72
     Heavenly
    2.70
    Activations Density 3.605%

    No Known Activations