© 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. 10337
    Prev
    Next
    INDEX
    Explanations

    installing and running code

    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
    ibold
    0.89
    rient
    0.88
    టన
    0.86
    loading
    0.84
     hẹn
    0.84
    miller
    0.81
    ழ
    0.81
    ಿತ
    0.80
    addTo
    0.80
    del
    0.79
    POSITIVE LOGITS
     Schra
    0.94
     메뉴
    0.91
     술
    0.91
     الجمهور
    0.90
     റെ
    0.89
     bū
    0.88
     READER
    0.87
     audience
    0.87
     diner
    0.84
     ауди
    0.84
    Activations Density 0.002%

    No Known Activations