© 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. 13-GEMMASCOPE-2-RES-16K
    7. 152
    Prev
    Next
    INDEX
    Explanations

    4357 HELP

    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
     lapsed
    0.67
     bonded
    0.64
     equate
    0.64
    0.64
     less
    0.63
     more
    0.61
     reduced
    0.61
     looser
    0.60
     >
    0.59
     limp
    0.58
    POSITIVE LOGITS
    AddTime
    0.86
     प्रतिनिधियों
    0.84
    ImageQueue
    0.83
    AddComponent
    0.81
     sebelumnya
    0.80
     nghiên
    0.79
    Wik
    0.79
    电视台
    0.78
    ocsát
    0.78
    QueueMutex
    0.78
    Activations Density 0.470%

    No Known Activations