© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9762
    Prev
    Next
    INDEX
    Explanations

    classic arcade

    np_acts-logits-general · gemini-2.5-flash-lite

    emulator, emulation, arcade, sprites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    anska
    0.41
    asad
    0.39
     Camino
    0.39
    katkan
    0.38
     Ambient
    0.38
    蟻
    0.38
     Kelas
    0.38
    nagar
    0.37
     $\}$
    0.37
     postdoctoral
    0.37
    POSITIVE LOGITS
     emulator
    1.16
     emulation
    1.13
    Emulator
    1.07
     Emulator
    1.04
     arcade
    1.03
    emulator
    1.01
     cartridge
    0.86
     Arcade
    0.85
     sprite
    0.82
     emulate
    0.82
    Activations Density 0.199%

    No Known Activations