© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8963
    Prev
    Next
    INDEX
    Explanations

    no matter

    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
    狙
    0.83
    bar
    0.82
     perf
    0.79
     লিপ
    0.79
     درج
    0.78
     Ч
    0.77
    task
    0.77
    탐
    0.76
    ाई
    0.75
     Task
    0.75
    POSITIVE LOGITS
     cabeza
    1.32
     cabeça
    1.28
     heads
    1.28
     Heads
    1.23
     head
    1.21
    头
    1.18
    Head
    1.15
    head
    1.14
    heads
    1.12
     头
    1.11
    Activations Density 0.039%

    No Known Activations