© 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
    2. Gemma-3-1B
    3. 17-GEMMASCOPE-2-RES-16K
    4. 416
    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
     persuading
    1.05
     plagiarism
    0.99
     aristocracy
    0.98
     postmodern
    0.96
     divor
    0.95
    抽象
    0.94
    ármaz
    0.94
    얻
    0.94
    stdint
    0.93
    Subtraction
    0.91
    POSITIVE LOGITS
     shutdown
    2.16
     reopened
    2.08
     reopen
    2.02
     reopening
    1.97
     operational
    1.97
     funcionamento
    1.96
     geöffnet
    1.94
     OPEN
    1.93
     Shutdown
    1.93
     shutdowns
    1.91
    Activations Density 4.053%

    No Known Activations