© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 5929
    Prev
    Next
    INDEX
    Explanations

    video games and consoles

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

    video games and consoles

    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_53_width_65k_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
     fuelwood
    0.46
    촘
    0.45
    쌤
    0.45
     (−
    0.44
     convening
    0.44
    encement
    0.43
    OLYBD
    0.43
    谒
    0.43
     unincorporated
    0.42
     eaves
    0.41
    POSITIVE LOGITS
     Xbox
    2.08
     PlayStation
    2.00
    Xbox
    2.00
     Nintendo
    1.91
    Nintendo
    1.91
     Wii
    1.91
     Playstation
    1.81
     xbox
    1.80
     console
    1.57
     Ubisoft
    1.55
    Activations Density 0.267%

    No Known Activations