© 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. 10475
    Prev
    Next
    INDEX
    Explanations

    function and method actions

    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
    اش
    0.97
    男子
    0.89
     Passenger
    0.81
     дэ
    0.80
     Weller
    0.78
    kere
    0.77
     Passengers
    0.76
    弱
    0.76
     коне
    0.76
    addTarget
    0.75
    POSITIVE LOGITS
     relocation
    0.91
     solution
    0.91
     respostas
    0.88
     haired
    0.88
     berdoa
    0.88
     reloc
    0.87
     dungeons
    0.87
     solutions
    0.87
     soluciones
    0.86
     rock
    0.86
    Activations Density 0.012%

    No Known Activations